JP7790109B2 - Text-to-speech system and text-to-speech device - Google Patents

Description

The present invention relates to a text-to-speech system and a text-to-speech device .

Patent Document 1 discloses application software that uses a smartphone's camera function to recognize characters on printed materials and reads the recognized characters aloud, making it possible to recognize small characters.

JP 2014-127197 A

However, while the application software in Patent Document 1 is useful for users with myopia or presbyopia, making printed materials easier to read, it simply reads out loud text, lacking in playfulness and not engaging for children or their families.

The present invention has been made in view of the above circumstances, and has as its object to provide a text-to-speech system and a text-to-speech device that can be enjoyed by children and their families.

The present application includes multiple means for solving the above problem, and one example is a voice reading system comprising an imaging device and a main unit having a mounting surface on which an object to be imaged can be placed, the imaging device comprising a gripping unit, a window for looking into the object, an imaging unit capable of imaging the object while the object is being looked into through the window, and a transmitting unit for transmitting image data captured by the imaging unit to the main unit, the main unit comprising a receiving unit for receiving the image data, an analyzing unit for analyzing the image data received by the receiving unit, and an output unit for outputting audio based on the analysis results of the analyzing unit.

This invention can be enjoyed by children and their families.

1 is a schematic perspective view showing an example of the configuration of a text-to-speech system according to a first embodiment; 1 is a block diagram showing an example of the configuration of a text-to-speech system according to a first embodiment; FIG. 10 is a schematic diagram showing an example of the configuration of a BGM list. FIG. 10 is an explanatory diagram showing an example of a sound. 10A and 10B are schematic diagrams illustrating an example of a method for correcting an imaging range by a correction unit. 10 is a flowchart illustrating an example of a processing procedure of the text-to-speech system according to the first embodiment. FIG. 1 is a block diagram showing an example of the configuration of a text-to-speech device. FIG. 10 is a block diagram showing an example of the configuration of a text-to-speech system according to a third embodiment. 11 is a flowchart illustrating an example of a processing procedure of the text-to-speech system according to the third embodiment. FIG. 10 is a diagram illustrating an example of a configuration of an information processing system according to a fourth embodiment. FIG. 13 is a diagram illustrating an example of a processing procedure of an information processing system according to a fourth embodiment. FIG. 10 is a diagram illustrating an example of a processing procedure of an interest analysis function. FIG. 10 is a diagram showing an example of an analysis result of an interest analysis function. FIG. 10 is a diagram illustrating an example of a processing procedure of an interest type analysis function. FIG. 10 is a diagram showing an example of an analysis result of an interest type analysis function. FIG. 10 is a diagram illustrating an example of a processing procedure of an activity type analysis function. FIG. 10 is a diagram showing an example of an analysis result of the activity type analysis function. FIG. 10 is a diagram illustrating an example of a processing procedure of a favorite color analysis function. FIG. 10 is a diagram showing an example of an analysis result of a favorite color analysis function. FIG. 13 is a diagram illustrating an example of a configuration of an information processing system according to a fifth embodiment. FIG. 13 is a diagram illustrating an example of a processing procedure of an information processing system according to a fifth embodiment. FIG. 13 is a diagram illustrating an example of a configuration of an information processing system according to a sixth embodiment. FIG. 13 is a diagram illustrating an example of a processing procedure of the imaging device 50 of the sixth embodiment. FIG. 10 is a diagram showing an example of a transition of interest analysis results. FIG. 10 is a diagram showing an example of the results of an interest analysis by age group, region, and time series.

(First embodiment)
Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is an external perspective view showing an example of the configuration of a text-to-speech system 100 according to a first embodiment. The text-to-speech system 100 includes an imaging device 50 and a main unit 10. The imaging device 50 includes a grip 62 and a window 61 provided on one end of the grip 62. The grip 62 is a portion that a user (e.g., an infant, a child, or their family) holds when holding the imaging device 50. The window 61 may be provided with a lens (magnifying glass), transparent resin or glass, or simply an opening, allowing the user to look through the window 61 into an object (e.g., a picture book, an illustrated guide, a children's book, etc.) to view an image (e.g., a character string such as a sentence, a diagram including a photograph, etc.) depicted in the object.

The imaging device 50 also includes an imaging unit 51 that can capture an image of the target when the target is viewed through the window 61, a distance sensor 52 that detects the distance to the target, and a button (shutter button) 63 that accepts an operation to start imaging using the imaging unit 51. The imaging unit 51 and distance sensor 52 are provided on one side of the grip 62 (the side facing the target when the target is viewed through the window 61), and the button 63 is provided on the other side of the grip 62 (the side facing the user's face when the target is viewed through the window 61). The imaging unit 51 can be composed of at least one camera. The distance sensor 52 can be any sensor that can detect distance. Instead of the distance sensor 52, distance can be measured according to the parallax of multiple cameras.

The main device 10 has a placement surface 21 on which an object can be placed. The placement surface 21 is rectangular in plan view and is inclined so that the height decreases from each of a pair of edge portions 22 that face the center portion 23 of the placement surface 21 toward the center portion 23. This allows picture books, illustrated guides, children's books, etc. to be placed on the placement surface 21 in a double-page spread, and the pages can be placed so that an angle of less than 180 degrees is formed between them, allowing the object to be placed in a way that makes the document or diagram easier to read.

The main unit 10 is equipped with restricting sections 24 that restrict the movement of objects on the other pair of edges of the placing surface 21 along the inclined direction of the placing surface 21. The restricting sections 24 are provided in a state where they protrude from the placing surface 21. This prevents picture books, illustrated guides, children's books, etc. placed on the placing surface 21 from slipping off the placing surface 21.

The main unit 10 has a storage section 25 formed on the mounting surface 21 for storing the imaging device 50. The shape of the storage section 25 in a plan view can be the same as the shape of the imaging device 50 in a plan view. The imaging device 50 may be configured to fit into the storage section 25, or the two may be attached together using a magnet or the like. This prevents the imaging device 50 from being lost and helps infants and children develop the habit of tidying up after themselves.

The main unit 10 may be provided with an indicator light (e.g., an LED) 26 that displays the status of the main unit 10. The indicator light 26 can display statuses such as powered, battery-powered, operating, charging, and abnormality. Although not shown, a touch-enabled display panel may also be provided. Required setting operations may be performed via the display panel.

Figure 2 is a block diagram showing an example of the configuration of the text-to-speech system 100 of the first embodiment. In addition to the aforementioned imaging unit 51 and distance sensor 52, the imaging device 50 also includes a correction unit 53, memory 54, processor 55, and communication unit 56. The processor 55 can control the entire imaging device 50. The memory 54 is composed of a semiconductor memory or the like, and can store image data obtained by imaging with the imaging unit 51.

The communication unit 56 realizes communication functionality with the main unit 10 via the home network 1, such as a wireless LAN. The imaging device 50 (e.g., the processor 55) can transmit image data captured by the imaging unit 51 (including image data temporarily stored in the memory 54) to the main unit 10 via the communication unit 56.

The correction unit 53 can correct the imaging range of the imaging unit 51 so that the imaging target within the field of view through the window unit 61 can be imaged according to the distance detected by the distance sensor 52. Details of the correction unit 53 will be described later.

The main unit 10 includes a control unit 11, a communication unit 12, an analysis unit 13, a voice synthesis unit 14, a sequence estimation unit 15, a memory unit 16, a microphone 17, a speaker 18, and an emotion index calculation unit 19. The analysis unit 13 includes a character string analysis unit 131 and a graphic analysis unit 132. The memory unit 16 is configured, for example, from semiconductor memory, and can store a background music list 161 and an audio data list 162. The control unit 11 can be configured with a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc.

The communication unit 12 realizes communication functions with the imaging device 50 via the home network 1. The communication unit 12 can receive image data transmitted by the imaging device 50.

The analysis unit 13 analyzes the image data received via the communication unit 12. Specifically, the analysis unit 13 performs image recognition on the image data received via the communication unit 12 to analyze whether the imaged subject is a character string or a picture. For image recognition, for example, a known method can be used, and processing such as preprocessing, feature extraction, matching, and classification can be performed.

The character string analysis unit 131 is equipped with an image processing engine and a language processing engine, and can analyze image data and output character strings (text). The process of extracting character strings from image data can be performed using, for example, a known method.

The image analysis unit 132 is equipped with an image processing engine and can analyze image data to determine what the images (including photographs) contained in the images represent. For example, imaged objects include, but are not limited to, vehicles such as trains and automobiles, animals, insects, and musical instruments.

The control unit 11 can output audio through the speaker 18 based on the analysis results of the analysis unit 13.

With the above-described configuration, infants and children can look at an object that catches their eye in a picture book, encyclopedia, or children's book through the window 61 of the imaging device 50 and press the button 63 to receive audio information about the object. This allows infants and children to have an audio experience that sparks their interest in objects and provides a fun experience. Furthermore, rather than simply playing with objects, by looking at something that infants and children are curious about or interested in, an audio experience is provided, providing a function that leads to new discoveries and provides the "fun of learning." Furthermore, family members (e.g., parents) can also enjoy the experience together with their infants and children.

Next, we will explain the first to third methods for preparing the audio to be output.

The first method involves recording text (sentences) found in picture books, encyclopedias, children's books, etc. in advance, and storing the recorded audio in the storage unit 16 as an audio data list 162. The audio data list 162 associates information indicating the text with audio data for each book, such as a picture book, encyclopedia, or children's book. Audio data corresponding to the character string (text) analyzed by the character string analysis unit 131 is output from the speaker 18 to perform "audio reading." When playing back recorded audio, the speaker's attributes may be changed. For example, a male or female voice, a young or elderly voice, or the voice of an anime voice actor may be set according to preference. Such settings may be made using a touch-enabled display panel. Alternatively, a parent's voice may be recorded using the microphone 17, and the recorded audio may be played back.

The second and third methods can be performed by the speech synthesis unit 14. First, the second method synthesizes speech by concatenating pre-recorded speech fragments. Specifically, speech can be synthesized by concatenating recorded characters (e.g., "a" and "ka"), words, and phrases. In this case, speech can be adjusted to sound more natural by adjusting the speaking rate, voice pitch, intonation (tone, intonation), etc. Corpus-based speech synthesis may also be used. Corpus-based speech synthesis is a technique that predicts fundamental frequency, phoneme duration, etc. based on linguistic features of the text, such as sentences, phrases, accent phrases, morphemes, phonemes, and accents, and then selects and concatenates speech fragments that best match the predicted fundamental frequency, phoneme duration, etc. from a pre-prepared speech database.

The third method synthesizes speech using speech features of pre-recorded speech. Specifically, the speech synthesis unit 14 is equipped with a trained model that has learned speech features from recorded speech. The speech synthesis unit 14 can convert speech into a speech waveform based on the speech features output by the trained model. Speech features include, for example, Mel-Frequency Cepstrum Coefficients (MFCC), line spectral pairs (LSP), fundamental frequency, etc.

Based on the analysis results of the analysis unit 13, the control unit 11 can output BGM (background music) via the speaker 18. This is explained in detail below.

The emotion index calculation unit 19 can calculate an emotion index by performing semantic analysis on the character string extracted by the character string analysis unit 131. For example, the emotion index calculation unit 19 can extract words that express emotions from the character string and calculate an emotion index based on the extracted words. Emotions are divided into positive emotions and negative emotions, and it is determined in advance whether each word that expresses an emotion is positive or negative. Furthermore, a value indicating the strength of the emotion is determined for each word that expresses an emotion. The emotion index calculation unit 19 can calculate an emotion index for the extracted character string based on the value of the strength of the emotion, whether each extracted word is positive or negative. The emotion index calculation unit may calculate an emotion index for, for example, a single paragraph or a group of multiple paragraphs.

The control unit 11 can use the BGM list 161 stored in the memory unit 16 to output BGM from the speaker 18 according to the emotion index calculated by the emotion index calculation unit 19.

Figure 3 is a schematic diagram showing an example of the configuration of the BGM list 161. The BGM list 161 defines the correspondence between emotional indices and BGM. Emotional indices can be, for example, positive levels 1 to 3 and negative levels 1 to 3. The higher the level number, the stronger the emotion. Multiple BGMs are associated with each level. For example, as shown in the figure, BGM1a, BGM1b, BGM1c, and BGM1d are associated with positive level 1. The same applies to other emotional indices. Here, the symbols a to d identify different scenes in a story or text found in a picture book, for example. For example, when the emotional index is positive level 1, the BGM can also be changed when the scene changes. This creates a sense of realism, making the audio experience more enjoyable and exciting.

The control unit 11 can also output a sound via the speaker 18 based on the analysis results of the analysis unit 13. Specifically, the control unit 11 can output a sound via the speaker 18 that is related to the analysis results (indicating what the figures (including photographs) included in the image represent) obtained by the diagram analysis unit 132.

Figure 4 is an explanatory diagram showing an example of sound. As shown in the figure, the imaged object (the image included in the image) can be, for example, a train, a car, an animal, an insect, or a musical instrument. If the image is a train, the sound of the train running is output. If the image is an animal, the animal's cry is output. If the image is a musical instrument, the sound of the instrument is output. In this way, when infants and children open an illustrated book or the like and look through the window 61 at an image that interests them, a sound related to the image they see is played. By looking into an object that they are curious about or interested in, they can find out what sound the object makes, leading them to new discoveries.

The order estimation unit 15 can estimate the reading order of character strings based on the arrangement (layout, etc.) of the character strings extracted by the character string analysis unit 131. For example, if the document layout is vertical, the reading order of character strings can be from top to bottom, and if the document layout is horizontal, the reading order of character strings can be from left to right. This makes it possible to read aloud whether the object is written vertically or horizontally.

Next, we will explain the correction unit 53.

Figure 5 is a schematic diagram showing an example of a method for correcting the imaging range using the correction unit 53. The correction unit 53 can correct the imaging range so that the imaging target within the range (field of view) visible within the frame of the window 61 can be captured, depending on the distance between the window 61 and the object, such as a picture book. As shown in the figure, when the position of the window 61 relative to the surface of the picture book is P1, the range visible when looking through the window 61 is defined as S1. Note that the imaging range S1 is rectangular, while the window 61 is circular. Therefore, technically, the field of view is circular. However, for convenience, the imaging range S1 is defined as a rectangle in which the circle is an inscribed circle. If the window 61 is moved slightly away from the picture book and the surface of the picture book is viewed at position P2, the distance between the window 61 and the picture book increases, and the range visible when looking through the window 61 increases. Therefore, the imaging range S2 is corrected to be larger than the imaging range S1.

Next, we will explain the operation of the text-to-speech system 100.

Figure 6 is a flowchart showing an example of the processing steps of the text-to-speech system 100 of the first embodiment. The imaging device 50 accepts a shutter button operation (S11), detects the distance to the object (S12), captures an image of the object (S13), and corrects the captured image data according to the distance to the object (S14). The imaging device 50 transmits the image data obtained by capturing the image to the main device 10 (S15), and the processing ends. Note that the imaging data may also be transmitted together with the subsequent analysis range without correcting the image data.

The main unit 10 receives the image data (S16) and determines whether the imaged subject is a character string (S17). If the imaged subject is a character string (YES in S17), the main unit 10 reads out the character string (S18). The main unit 10 calculates an emotion index based on the character string (S19) and outputs background music corresponding to the emotion index (S20).

The main unit 10 determines whether the scene has changed based on the character string (S21). If the scene has changed (YES in S21), it changes the background music and outputs it (S22), and ends the process. If the scene has not changed (NO in S21), the main unit 10 ends the process.

If the image capture target is not a character string in step S17 (NO in S17), the main unit 10 determines whether the image capture target is a picture (S23). If the image capture target is a picture (YES in S23), the main unit 10 outputs a sound related to the content of the picture that is the image capture target (S24), as shown in FIG. 4, and ends the process. If the image capture target is not a picture (NO in S23), the main unit 10 ends the process.

Second Embodiment
In the first embodiment, the text-to-speech system 100 was configured to include an imaging device 50 and a main body device 10, but in the second embodiment, the functions of the main body device 10 are incorporated into the imaging device 50 to form a text-to-speech device.

Figure 7 is a block diagram showing an example of the configuration of the text-to-speech device 200. The external shape of the text-to-speech device 200 is similar to that of the imaging device 50 of the first embodiment, and includes a grip, a shutter button, and a window. The text-to-speech device 200 includes a control unit 201, an imaging unit 202, a distance sensor 203, a correction unit 204, an analysis unit 205 having a character string analysis unit 206 and a figure analysis unit 207, a voice synthesis unit 208, an order estimation unit 209, a memory unit 210 that stores a background music list 211 and an audio data list 212, a microphone 213, a speaker 214, and an emotion index calculation unit 215. The functions of the control unit 201, imaging unit 202, distance sensor 203, correction unit 204, analysis unit 205 having a character string analysis unit 206 and a graphic analysis unit 207, voice synthesis unit 208, order estimation unit 209, memory unit 210 storing a BGM list 211 and a voice data list 212, microphone 213, speaker 214, and emotion index calculation unit 215 are the same as in the first embodiment, so description thereof will be omitted.

(Third embodiment)
The third embodiment is configured to include an imaging device 50 and a main body device 30, as in the first embodiment, and further includes a server 300, in which the main functions of the main body device 10 of the first embodiment are incorporated.

Figure 8 is a block diagram showing an example of the configuration of a text-to-speech system according to the third embodiment. The imaging device 50 has the same configuration as the imaging device 50 according to the first embodiment. The main device 30 includes a control unit 36, a first communication unit 31, a second communication unit 32, a memory unit 33 that stores a background music list 331, a microphone 34, and a speaker 35.

The first communication unit 31 realizes communication functions with the imaging device 50 via the home network 1.

The second communication unit 32 realizes communication functions with the server 300 via a communication network 2 such as the Internet. The BGM list 331, microphone 34, and speaker 35 are the same as in the first embodiment, so their description will be omitted.

The server 300 includes a control unit 301, a communication unit 302, an analysis unit 303 having a character string analysis unit 304 and a figure analysis unit 305, a voice synthesis unit 306, an order estimation unit 307, a memory unit 308 that stores a voice data list 309, and an emotion index calculation unit 310.

The communication unit 302 realizes communication functions with the main device 30 via the communication network 2. The functions of the control unit 301, analysis unit 303, character string analysis unit 304, graphic analysis unit 305, speech synthesis unit 306, order estimation unit 307, speech data list 309, and emotion index calculation unit 310 are the same as in the first embodiment, so explanations will be omitted.

Figure 9 is a flowchart showing an example of the processing procedure of the text-to-speech system of the third embodiment. The processing of the imaging device 50 is the same as in the first embodiment, so a description thereof is omitted. The main device 30 receives image data transmitted by the imaging device 50 (S31) and transmits the received image data to the server 300 (S32).

The server 300 receives the image data (S33) and determines whether the imaged object is a character string (S34). If the imaged object is a character string (YES in S34), the server 300 converts the character string into audio data and transmits the converted audio data to the main device 30 (S35). The main device 30 outputs audio (S36). This allows the character string to be read aloud.

The server 300 calculates an emotion index based on the character string (S37) and transmits the calculated emotion index to the main device 30 (S38). The main device 30 receives the emotion index (S39) and outputs background music according to the received emotion index (S40).

The server 300 determines whether the scene has changed based on the character string (S41), and if the scene has changed (YES in S41), it notifies the main device 30 of the scene change (S42). The main device 30 changes the background music and outputs it (S43). If the scene has not changed (NO in S41), the server 300 ends the process.

In step S34, if the imaging target is not a character string (NO in S34), the server 300 determines whether the imaging target is a picture (S44). If the imaging target is a picture (YES in S44), the server 300 transmits sound data relating to the content of the picture to the main device 30 (S45) and ends the process. The main device 30 receives the sound data and outputs sound based on the received sound data (S46), and ends the process. If the imaging target is not a picture (NO in S44), the server 300 ends the process.

The text-to-speech system and text-to-speech device of this embodiment can be used by infants and children for play at home, at facilities such as nurseries and kindergartens, and at temporary care facilities (for example, shopping malls, supermarkets, beauty salons, etc.). Furthermore, users are not limited to infants and children; elderly people, foreigners, and people with disabilities may also use the text-to-speech system and text-to-speech device of this embodiment.

The imaging device, main unit, and text-to-speech device of the text-to-speech system of this embodiment can be sold or rented to users as toys. It is also possible to provide server functions on the cloud and receive usage fees in return.

(Fourth embodiment)
In the fourth embodiment, we will explain an information processing device system, information processing device, imaging device, etc. that uses functions similar to those of the above-mentioned voice reading system 100 to allow parents and other guardians to understand the interests of their children, such as young children (especially the latest interests and changes in interests due to growth or environmental changes, etc.).

In recent years, the number of dual-income households has increased, and parents are increasingly leaving their children in daycare centers, making it difficult for them to observe their children's daytime behavior and understanding what their children are beginning to become interested in, or if they even have any. Parents are unable to properly grasp the growth and changes in their children that occur little by little every day.

Furthermore, approaches to fostering intellectual curiosity in early childhood education are often one-size-fits-all or broad-based in order to suit many children, and do not take into account the changes in each individual's intellectual curiosity, interests, and preferences. In order to solve these issues, the following embodiment describes support for fostering interests that are tailored to each individual, taking into account the real-time state of interests and preferences, as well as the child's growth and changes in the environment.

Figure 10 is a diagram showing an example of the configuration of an information processing system according to the fourth embodiment. The information processing system includes an imaging device 50, a terminal device 100, and a server 400 as an information processing device. The imaging device 50 has the same configuration as in the first embodiment, but differs in that a speaker 57 is built into the imaging device 50. The imaging device 50 can capture an image of an imaging target in a reading mode or a sound effect playback mode. The reading mode or sound effect playback mode may be switched manually using a switch or button, or may be switched automatically based on the analysis results of the analysis unit 403 of the server 400. The imaging device 50 is a magnifying glass-like device that infants and children play with, and the terminal device 100 is a terminal carried by a parent or guardian.

The terminal device 100 has a configuration similar to that of the main device 30 of the third embodiment, but differs in that it includes a display unit 104 and an operation unit 105. The control unit 101, first communication unit 102, second communication unit 103, and memory unit 106 are similar to the control unit 36, first communication unit 31, second communication unit 32, and memory unit 33 of the main device 30 of the third embodiment. The terminal device 100 may be configured as, for example, a smartphone, a tablet terminal, or the like. The display unit 104 may be configured as a liquid crystal display or an organic EL (Electro Luminescence) display. The operation unit 105 may be configured as a touch panel or the like, and may be used to input characters on the display unit 104 and to operate icons, images, or characters displayed on the display unit 104.

The server 400 includes a control unit 401 that controls the entire server 400, a communication unit 402, an analysis unit 403, an order estimation unit 406, a voice synthesis unit 407, a sound playback unit 408, an analysis unit 409, and a memory unit 410. The analysis unit 403 includes a character string analysis unit 404 and a figure analysis unit 405. The memory unit 410 stores a voice data list 411. The control unit 401, communication unit 402, analysis unit 403, character string analysis unit 404, figure analysis unit 405, order estimation unit 406, voice synthesis unit 407, and memory unit 410 are similar to the control unit 301, communication unit 302, analysis unit 303, character string analysis unit 304, figure analysis unit 305, order estimation unit 307, voice synthesis unit 306, and memory unit 308 of the server 300 of the third embodiment. The analysis unit 403 may automatically switch between sound effect playback mode and reading mode depending on the analysis result, which is whether the imaged object is a picture or a character string. The sound playback unit 408 has the same sound playback function as the control units 11, 301, etc. Details of the analysis unit 409 will be described later.

Figure 11 is a diagram showing an example of the processing procedure of the information processing system of the fourth embodiment. The imaging device 50 captures an image of the object to be imaged (S101) and transmits the image data obtained by the image capture to the terminal device 100 (S102). The terminal device 100 receives the image data (S103) and transmits the received image data to the server 400 (S104).

The server 400 receives the image data (S105) and analyzes the imaged object based on the received image data (S106). Depending on whether the imaged object is a figure or a string of characters, the server 400 generates a sound related to the content of the figure or a voice reading out the string of characters (S107). The sound related to the content of the figure and the voice reading out the string of characters may be collectively referred to as "voice."

The server 400 transmits the generated sound or audio to the terminal device 100 (S108). The terminal device 100 receives the sound or audio (S109) and transmits the received sound or audio to the imaging device 50 (S110). The imaging device 50 receives the sound or audio (S111) and outputs the received sound or audio (S112).

The server 400 records the received image data and analysis results in the storage unit 410 (S113) and updates the number of times the sound is played or the voice is read aloud (S114). Each time a user such as an infant or child takes an image of an object with the imaging device 50, the process shown in FIG. 11 is repeated, and information such as the image data, analysis results, and number of times the sound is played or the voice is read aloud can be collected.

The control unit 401 functions as a collection unit and collects image data obtained by capturing images of the imaging target via the communication unit 402. The analysis unit 409 analyzes the interests of the user (infant or child) who captured the image of the imaging target based on the collected image data. The control unit 401 functions as a provision unit and can provide the analysis results of the analysis unit 409.

In this way, image data of subjects captured by infants and children that interest them can be collected as part of a life log, and the infant's or child's daily interests can be analyzed based on the collected life log. The analysis results can then be fed back to parents, allowing parents to follow up and support their infants and children in accordance with their interests. For example, parents can buy their children goods related to areas that interest them, or take them to places or facilities that interest them.

Next, the analysis process performed by the analysis unit 409 will be described in detail. The analysis unit 409 has various functions, such as (1) an interest analysis function, (2) an interest type analysis function, (3) an activity type analysis function, and (4) a favorite color analysis function. The life log to be analyzed can be image data captured and collected by the imaging device 50, and the number of times the reading mode and sound effect playback mode are used. Each analysis function will be described below.

Figure 12 is a diagram showing an example of the processing procedure for the interest analysis function. For convenience, the following description will be given with the control unit 401 as the subject of processing. The control unit 401 collects image data (S121) and determines whether the data has been collected for a first predetermined period (S122). The first predetermined period can be, for example, one week, but is not limited to this. If the data has not been collected for the first predetermined period (NO in S122), the control unit 401 continues processing in step S121.

If the images have been collected over the first predetermined period (YES in S122), the control unit 401 classifies the imaged objects by category (S123). Specifically, the analysis unit 409 classifies the imaged objects by category. The analysis unit 409 may be equipped with a learning model for object detection. Examples of learning models include HOG (Histogram of Oriented Gradients), R-CNN (Region-based CNN), Fast R-CNN, RPN (Region Proposal Network), YOLO (You Only Look Once), SSD (Single Shot Detector), and Transformer. The objects detected by the analysis unit 409 can be classified by category. Categories can be determined as appropriate, for example, trains, cars, airplanes, flowers, animals, food, musical instruments, fish, insects, dolls, etc.

The control unit 401 calculates the total number of objects captured for each category (S124). For example, if a child captures 20 images of objects classified as "trains" over the course of a week, the number of "trains" is set to 20. The control unit 401 registers the fields with the most images as "interesting" categories (S125). For example, the control unit 401 calculates the number of images captured for each category, and registers the top five fields with the most images captured as "interesting" categories. Note that the number of "interesting" categories is not limited to five.

The control unit 401 compares the number of images taken by each category in the most recent first predetermined period (e.g., last week) and registers as a "rapidly rising" category any category in which the number of images taken by each category in the current first predetermined period (e.g., this week) is on the rise (S126). For example, the difference between the number of images taken by each category in last week and this week can be calculated, and any category in which the calculated difference is equal to or greater than a predetermined difference threshold can be registered as a "rapidly rising" category. Alternatively, the category in which the calculated difference is the largest can be registered as a "rapidly rising" category.

The control unit 401 registers the field with the most appearances among the number of images taken for each field as "my fad" (S127). For example, the field with the most objects taken in one week can be designated as "my fad."

The control unit 401 transmits the analysis results ("Interested," "Rapidly Rising," "My Craze") to the terminal device 100, which then displays the analysis results. The control unit 401 then provides the analysis results (S128) and terminates the process. Note that the words "Interested," "Rapidly Rising," and "My Craze" are merely examples, and the present invention is not limited to these words.

As described above, the analysis unit 409 functions as a first analysis unit and can analyze the field of the image subject based on the collected image data. The analysis unit 409 may also analyze the interests of infants and children (users) based on the analysis results collected each time a first predetermined period of time is reached.

The analysis unit 409 may analyze the user's "interested" (first indicator) based on the number of subjects captured for each analyzed field. This allows parents to provide appropriate support and encouragement to their children without missing their child's "beginning of interest."

The analysis unit 409 may analyze a "rapid increase" (second indicator) related to the user's interests based on changes in the number of subjects photographed for each field for each first predetermined period. Furthermore, the analysis unit 409 may analyze a "current fad" (third indicator) related to the user's interests based on the field with the largest number of subjects photographed among the number of subjects photographed for each field.

Figure 13 is a diagram showing an example of the analysis results of the interest analysis function. The "OO-chan's interest analysis results" screen 501 shown in Figure 13 can be displayed on the display unit 104 of the terminal device 100. The "OO-chan's interest analysis results" screen 501 has a message display area 502 that displays an error message such as "The date is incorrect," a display area 503 that displays the ratio of subjects photographed this week by category, a display area 505 that displays "interesting" categories, a display area 506 that displays "current obsession" categories, and a display area 507 that displays "trending" categories. In addition, a "View all logs" icon 504 is displayed to view all logs.

In the example of Figure 13, the "interesting" categories are displayed as "Trains," "Flowers," "Cars," "Food," and "Animals," and the number of photos taken in each category is displayed as 20, 18, 15, 10, and 9, respectively. In "My Craze," for example, the object with the most photos (in the example of Figure 13, an image of a "Bullet Train") is displayed from the "Trains" category, which has the most photos taken, along with a message such as "My current craze is the Bullet Train!" This allows parents to easily grasp their child's real-time interests and tastes. In "Trending," a message such as "It seems he's recently become interested in 'Food'" is displayed. This allows parents to appropriately grasp changes in interests and tastes, which can be useful in daily communication with their children and in their daily lives (such as purchasing activities).

Figure 14 is a diagram showing an example of the processing procedure for the interest type analysis function. The control unit 401 compares the "interested" rankings for the most recent first predetermined period (e.g., last week) with the "interested" rankings for the current first predetermined period (e.g., this week) (S131) and determines whether there has been a change in the top rankings (S132). For example, as shown in Figure 13, if the "interested" rankings are displayed from 1st to 5th, the top rankings can be, but are not limited to, the first and second rankings. If the top two rankings last week were, for example, "animals" and "flowers," and the top two rankings this week are, for example, "trains" and "flowers," then the top ranking has changed from "animals" to "trains" from last week to this week, and in this case, it can be determined that there has been a change in the top rankings.

If there is a change in the top rankings (YES in S132), the control unit 401 classifies the user's interest type as "curious" (S133), provides the analysis results (interest type) to the terminal device 100 (S134), and ends the process.

If there is no change in the top rankings (NO in S132), the control unit 401 determines whether there is any change in the rankings (S135). If there is no change in the rankings (YES in S135), that is, if there is no change in the rankings from 1st to 5th place between last week and this week, the control unit 401 classifies the user's interest type as the "contemplative doctor" type (S136) and performs the processing of step S134.

If there is a change in the rankings (NO in S135), that is, if there is a change in the lower rankings excluding the top rankings (e.g., rankings from 3rd to 5th), the control unit 401 classifies the user's interest type as "intermediate" (S137) and performs the processing of step S134. Furthermore, a change in rankings may be determined not only by a change in the top or bottom rankings, but also by a change in the overall rankings. For example, a change may be determined based on what percentage of the rankings from the top to a predetermined number (the predetermined number is variable) (e.g., the top 20) in the weekly rankings sorted by the number of detections have changed. For example, if N% or more of the rankings have changed, the user may be determined to be "curious," whereas if N% or less of the rankings have not changed, the user may be determined to be "thoughtful doctor," and in all other cases, the user may be determined to be "intermediate." The value N can be set as appropriate. Note that the terms "curious," "thoughtful doctor," and "intermediate" are merely examples and are not limited to these terms.

As described above, the analysis unit 409 functions as an identification unit, and may identify changes in "interested" (first indicator) analyzed for each first predetermined period, and analyze the user's type of interest based on the identified change in "interested."

Figure 15 is a diagram showing an example of the analysis results of the interest type analysis function. The "OO-chan's interest analysis results" screen 511 shown in Figure 15 can be displayed on the display unit 104 of the terminal device 100. The "OO-chan's interest analysis results" screen 511 has, for example, a message display area 502 that displays error messages, a display area 512 that displays interest types, and a display area 514 that displays this week's log.

In the example of Figure 15, the interest type is displayed as "OO-chan is a 'curious' type and is interested in a variety of things." This allows parents to understand their child's interest type and provide follow-up and support that matches their child's interest type. By operating the "Select Photo" icon 513, parents can display a desired photo from among photos of their child stored on the terminal device 100 or photos of their child uploaded from another smartphone or PC.

This week's log can display rankings of "interesting" categories, the percentage of objects photographed this week by category, and "trending" categories. By operating the "View details" icon 515, the rankings of "interesting" categories can be displayed in more detail. Additionally, by operating the "View last week's log" icon 516, last week's log can be displayed instead of or in addition to this week's log.

This allows parents to accurately grasp their child's interests and can use this information in their daily communication with their children and in their daily lives (such as purchasing activities).

Figure 16 shows an example of the processing procedure for the activity type analysis function. The control unit 401 records the number of times the sound effects playback function and the reading function are used (S141) and determines whether the recording has been completed over a third predetermined period (S142). The number of times the sound effects playback function and the reading function are used is the number of times they are used in sound effects playback mode and reading mode. The sound effects playback mode and reading mode can be set manually or automatically. The third predetermined period can be, for example, one month, but is not limited to this.

If recording has not been performed for the third predetermined period (NO in S142), the control unit 401 continues processing in step S141. If recording has been performed for the third predetermined period (YES in S142), the control unit 401 determines whether the proportion of the number of times the sound effects playback function has been used is equal to or greater than M% of the total (S143). The total is the total number of times the sound effects playback function has been used and the reading function has been used. The value of M is variable and can be changed as appropriate. If the proportion of the number of times the sound effects playback function has been used is equal to or greater than M% of the total (YES in S143), the control unit 401 classifies the user's activity type as "explorer type" (S144), provides the analysis result (activity type) to the terminal device 100 (S145), and ends processing.

If the percentage of times the sound effect playback function has been used is less than M% of the total (NO in S143), the control unit 401 determines whether the percentage of times the reading function has been used is more than M% of the total (S146). If the percentage of times the reading function has been used is more than M% of the total (YES in S146), the control unit 401 classifies the user's activity type as the "bookworm type" (S147) and performs the processing of step S145. If the percentage of times the reading function has been used is less than M% of the total (NO in S146), the control unit 401 classifies the user's activity type as the "very interested type" (S148) and performs the processing of step S145.

As described above, the analysis unit 403 functions as a third analysis unit and can analyze whether the imaged object is a string of characters or a figure based on the collected image data. The voice synthesis unit 407 functions as a reading unit and can read out the string of characters if the imaged object is analyzed to be a string of characters. The sound playback unit 408 functions as a playback unit and can play back sound related to the content of the figure if the imaged object is analyzed to be a figure. The analysis unit 409 may analyze the user's activity type based on the number of times the voice synthesis unit 407 reads out the text and the number of times the sound playback unit 408 plays it back over a third predetermined period (e.g., one month).

Figure 17 is a diagram showing an example of the analysis results of the activity type analysis function. The "OO-chan's Interests Analysis Results" screen 521 shown in Figure 17 can be displayed on the display unit 104 of the terminal device 100. The "OO-chan's Interests Analysis Results" screen 521 has, for example, a message display area 502 that displays error messages, a display area 522 that displays activity types, and a display area 514 that displays this week's log.

In the example of Figure 17, the activity type is displayed as "OO-chan is an 'explorer' type who likes to play by exploring various things." This allows parents to understand their child's activity type and provide follow-up and support that matches their child's activity type. By operating the "Select Photo" icon 513, parents can display a desired photo from among photos of their child recorded on the terminal device 100 or photos of their child uploaded from another smartphone or PC.

This week's log is the same as in Figure 15, so a detailed explanation will be omitted. In this way, parents can accurately grasp their child's activity type, which can be useful in daily communication with their child and in daily life (such as purchasing activities).

Figure 18 shows an example of the processing procedure for the favorite color analysis function. The control unit 401 collects image data (S151) and determines whether the data has been collected for a second predetermined period (S152). The second predetermined period can be, for example, one week, but is not limited to this. If the data has not been collected for the second predetermined period (NO in S152), the control unit 401 continues processing in step S151.

If the data has been collected over a second predetermined period (YES in S152), the control unit 401 classifies the colors contained in the imaged subject (S153). Specifically, the analysis unit 409 is equipped with a learning model with a color analysis function, and can detect the colors of areas within the image and the colors used within the image. The analysis unit 409 can classify colors by frequently occurring colors.

The control unit 401 calculates the total number of objects captured for each color (S154). That is, the total number of objects detected for each classified color can be calculated. For example, if a child captures 20 images of objects classified as yellow over the course of a week, the number of "yellow" objects is set to 20. The control unit 401 registers the color captured the most as the "favorite color" (S155).

The control unit 401 compares the number of images taken for each color in the most recent second predetermined period (e.g., last week) and registers the color for which the number of images taken for each color in the current second predetermined period (e.g., this week) is on an increasing trend as a "rapidly rising" color (S156). For example, the difference between the number of images taken for each color last week and this week can be calculated, and colors for which the calculated difference is equal to or greater than a predetermined difference threshold can be registered as "rapidly rising" colors. Alternatively, the color for which the calculated difference is the largest can be registered as a "rapidly rising" color.

The control unit 401 provides the analysis results ("Favorite Color", "Rapidly Rising") to the terminal device 100 (S157), and ends the process. Note that the words "Favorite Color" and "Rapidly Rising" are merely examples and are not limited to these words.

As described above, the analysis unit 409 functions as a second analysis unit and analyzes the colors contained in the image capture subject based on the collected image data. The analysis unit 409 may analyze the user's color interests based on the analysis results collected each time a second predetermined period of time is reached.

Figure 19 is a diagram showing an example of the analysis results of the favorite color analysis function. The "OO-chan's Color Preference Analysis Results" screen 531 shown in Figure 19 can be displayed on the display unit 104 of the terminal device 100. The "OO-chan's Color Preference Analysis Results" screen 531 has, for example, a message display area 502 that displays an error message, a display area 532 that displays an image of a favorite color, a display area 533 that displays a favorite color, and a display area 534 that displays a "trending" color.

Display area 532 displays images 1-4, each drawn in the user's favorite color (yellow), with the phrase "OO-chan seems to particularly like yellow!". Images 1-4 may be switched to a different image from the life log after a certain period of time has passed. The ranking of favorite colors (in the example of Figure 19, first place is "yellow," second place is "red," and third place is "blue") is also displayed.

Display area 533 displays the number of objects detected for each color, in order of favorite color. In the example of Figure 19, the following numbers are displayed: "yellow" 20, "red" 18, "blue" 15, "orange" 10, and "green" 7. "Green" is a color that has shown an increasing number of photographs this week when comparing last week's analysis results with this week's analysis results, and is labeled "Rapidly Rising!"

Display area 534 displays a message such as "It seems he has recently become interested in 'green,'" along with images 1 and 2 drawn in green. This allows parents to easily understand in real time which colors their child has become interested in and which colors they like. Parents can also accurately grasp changes in colors of interest, which can be useful in daily communication with their children and in daily life (such as purchasing activities). In the above example, the interest types shown in Figure 15, the activity types shown in Figure 17, and the preferred color analysis shown in Figure 19 were explained using separate figures for convenience, but these are just examples, and the interest types, activity types, and preferred color analysis can be displayed simultaneously on the same screen.

Fifth Embodiment
In the fourth embodiment, the analysis function is provided in the server 400, but the present invention is not limited to this. In the fifth embodiment, a configuration in which the analysis function is provided in a terminal device will be described.

Figure 20 is a diagram showing an example of the configuration of an information processing system of the fifth embodiment. The information processing system includes an imaging device 50 and a terminal device 150 as an information processing device. The imaging device 50 is the same as in the fourth embodiment. Compared to the fourth embodiment, the terminal device 150 differs in that it includes an analysis unit 155, a character string analysis unit 156, a figure analysis unit 157, an order estimation unit 158, a voice synthesis unit 159, a sound playback unit 160, an analysis unit 161, an audio data list 163, and a computer program 164. The analysis unit 155, character string analysis unit 156, figure analysis unit 157, order estimation unit 158, speech synthesis unit 159, sound reproduction unit 160, analysis unit 161, and speech data list 163 are similar to the analysis unit 403, character string analysis unit 404, figure analysis unit 405, order estimation unit 406, speech synthesis unit 407, sound reproduction unit 408, analysis unit 409, and speech data list 411 provided in the server 400 of the fourth embodiment. When executed by the control unit 151, the computer program 164 can realize all or part of the functions of the analysis unit 155, character string analysis unit 156, figure analysis unit 157, order estimation unit 158, speech synthesis unit 159, sound reproduction unit 160, and analysis unit 161.

Figure 21 is a diagram showing an example of the processing procedure of the information processing system of the fifth embodiment. The imaging device 50 captures an image of the imaging target (S161) and transmits the image data obtained by capturing the image to the terminal device 150 (S162). The terminal device 150 receives the image data (S163) and analyzes the imaging target based on the received image data (S164). The terminal device 150 generates a sound related to the content of the image or a voice that reads out the text, depending on whether the imaging target is a picture or a string of characters (S165).

The terminal device 150 transmits the generated sound or voice to the imaging device 50 (S166). The imaging device 50 receives the sound or voice (S167) and outputs the received sound or voice (S168). The terminal device 150 records the received image data and analysis results in the storage unit 162 (S169) and updates the number of times the sound is played or the voice is read aloud (S170). Each time a user, such as an infant or child, captures an image of an object with the imaging device 50, the process shown in FIG. 21 is repeated, and information such as the image data, analysis results, and number of times the sound is played or the voice is read aloud can be collected. Note that the same processes as those in FIGS. 12 to 19 are performed in the fifth embodiment, so a description thereof will be omitted.

The control unit 151 functions as a collection unit and collects image data obtained by capturing images of the imaging target via the communication unit 152. The analysis unit 161 analyzes the interests of the user (infant or child) who captured the image of the imaging target based on the collected image data. The control unit 151 functions as a provision unit and can provide the analysis results of the analysis unit 161.

In addition, the computer program 164 running on the terminal device 150 causes the computer to execute processing to collect image data obtained by capturing images of the subject, analyze the interests of the user who captured the image based on the collected image data, and provide the analysis results.

In this way, image data of subjects captured by infants and children that interest them can be collected as part of a life log, and the infant's or child's daily interests can be analyzed based on the collected life log. The analysis results can then be fed back to parents, allowing parents to follow up and support their infants and children in accordance with their interests. For example, parents can buy their children goods related to areas that interest them, or take them to places or facilities that interest them.

Sixth Embodiment
In the sixth embodiment, a configuration in which an analysis function is provided in an imaging device will be described.

Figure 22 is a diagram showing an example of the configuration of an information processing system according to the sixth embodiment. The information processing system includes an imaging device 50 and a terminal device 100. The terminal device 100 is the same as that of the fourth embodiment. The imaging device 50 differs from that of the fourth embodiment in that it includes an analysis unit 71, a character string analysis unit 72, a graphic analysis unit 73, an order estimation unit 65, a voice synthesis unit 66, a sound reproduction unit 67, an analysis unit 68, and a voice data list 70. The analysis unit 71, character string analysis unit 72, graphic analysis unit 73, order estimation unit 65, voice synthesis unit 66, sound reproduction unit 67, analysis unit 68, and voice data list 70 are the same as the analysis unit 403, character string analysis unit 404, graphic analysis unit 405, order estimation unit 406, voice synthesis unit 407, sound reproduction unit 408, analysis unit 409, and voice data list 411, respectively, included in the server 400 according to the fourth embodiment.

Figure 23 is a diagram showing an example of the processing procedure of the imaging device 50 of the sixth embodiment. The imaging device 50 captures an image of the imaging target (S181) and analyzes the imaging target based on the image data obtained by capturing the image (S182). Depending on whether the imaging target is a figure or a string of characters, the imaging device 50 generates a sound related to the content of the figure or a voice that reads out the string of characters (S183).

The imaging device 50 outputs the generated sound or voice (S184). The imaging device 50 records the image data and analysis results in the storage unit 69 (S185), and updates the number of times the sound is played or the voice is read aloud (S186). Each time a user, such as an infant or child, takes an image of an object with the imaging device 50, the process shown in FIG. 23 is repeated, and information such as the image data, analysis results, and number of times the sound is played or the voice is read aloud can be collected. Note that the same processes as those in FIGS. 12 to 19 are performed in the sixth embodiment, so a description thereof will be omitted.

The imaging device 50 includes a gripping unit 62, a window 61 for looking into the imaging target, an imaging unit 51 capable of imaging the imaging target while the imaging target is being looked into through the window 61, an analysis unit 68 that analyzes the interests of the user who captured the imaging target based on image data captured and collected by the imaging unit 51, and a control unit 11 that serves as a providing unit that provides the analysis results of the analysis unit 68.

In this way, image data of subjects captured by infants and children that interest them can be collected as part of a life log, and the infant's or child's daily interests can be analyzed based on the collected life log. The analysis results can then be fed back to parents, allowing parents to follow up and support their infants and children in accordance with their interests. For example, parents can buy their children goods related to areas that interest them, or take them to places or facilities that interest them.

In the fourth to sixth embodiments, the analysis function was provided in either the server 400, the terminal device 150, or the imaging device 50, but the analysis function may be distributed among at least two of the server 400, the terminal device 150, and the imaging device 50.

Figure 24 shows an example of the transition of interest analysis results. By collecting interest analysis results for users such as infants and children as they grow, it is possible to understand the transition of each individual user's interest analysis results. In the example of Figure 24, the transition of "My Craze" categories (e.g., categories A1-A5) and "Rapidly Trending" categories (e.g., categories B1-B5) is displayed along with the user's age. Categories A1-A5 and B1-B5 may also include shared categories. By collecting data such as that shown in Figure 24 for a large number of users, it can be utilized as big data. It is also possible to predict how individual users' interests will change and transition in the future.

Figure 25 shows an example of the results of an interest analysis by age group, region, and time series. By collecting the analysis results of a large number of children, differences in interest trends by age group, region, and time series can be understood. This allows for understanding time-series trends and future predictions for any group (user group), such as by age group, region, or nursery school. Figure 25A shows the results of an analysis of interest fields by age group A1, A2, A3, etc. For convenience, the interest fields are labeled C1 through C5, but the number of fields is not limited to this number. The interest fields for each age group may be represented in a diagram similar to a radar chart. Figure 25B shows the results of an analysis of interest fields by region L1, L2, L3, etc. For convenience, the interest fields are labeled C1 through C5, but the number of fields is not limited to this number. The interest fields for each region may be represented in a diagram similar to a radar chart. Figure 25C shows the results of an analysis of interest fields by time elapsed since a specified reference point (e.g., a specific age). For convenience, the fields of interest are designated C1 to C5, but the number of fields is not limited to this. The fields of interest at each point in time may be represented in a diagram such as a radar chart. As described above, the analysis unit 409 may analyze the temporal changes in the interests of a group of users divided by at least one of age and region based on the collected image data (for example, including time-series changes for each group or future predictions).

The text-to-speech system of this embodiment comprises an imaging device and a main unit having a mounting surface on which an object to be imaged can be placed, the imaging device comprising a gripping unit, a window for looking into the object, an imaging unit capable of imaging the object while looking into the object through the window, and a transmitting unit for transmitting image data captured by the imaging unit to the main unit, the main unit comprising a receiving unit for receiving the image data, an analyzing unit for analyzing the image data received by the receiving unit, and an output unit for outputting audio based on the analysis results of the analyzing unit.

In the text-to-speech system of this embodiment, the placement surface is rectangular in plan view and is inclined so that the height decreases from each of a pair of edges that sandwich the center of the placement surface toward the center.

In the text-to-speech system of this embodiment, the main device is equipped with a restricting unit that restricts movement of the object on another pair of edges of the placement surface along the inclined direction of the placement surface.

In the text-to-speech system of this embodiment, the main unit has a storage section formed on the placement surface for storing the imaging device.

In the text-to-speech system of this embodiment, the imaging device includes a detection unit that detects the distance to the object, and a correction unit that corrects the imaging range of the imaging unit so that the object within the field of view through the window can be imaged in accordance with the distance detected by the detection unit.

In the text-to-speech system of this embodiment, the analysis unit analyzes whether the imaged object is a character string or a figure based on the image data received by the receiving unit, and if the analysis unit analyzes that the imaged object is a character string, the output unit outputs a voice that reads out the character string.

In the text-to-speech system of this embodiment, when the analysis unit analyzes that the imaged object is a diagram, the output unit outputs a sound related to the content of the diagram.

The text-to-speech system of this embodiment includes an emotional index calculation unit that, when the analysis unit analyzes that the imaged object is a character string, performs a semantic analysis of the character string to calculate an emotional index, and the output unit outputs background music according to the emotional index calculated by the emotional index calculation unit.

The text-to-speech system of this embodiment includes a reading order estimation unit that, when the analysis unit analyzes that the imaged object is a string of characters, estimates the reading order of the string of characters based on the arrangement of the string of characters.

The text-to-speech system of this embodiment includes a speech synthesis unit that synthesizes speech using speech features of pre-recorded speech, and when the analysis unit analyzes that the imaged object is a character string, the output unit outputs the speech synthesized by the speech synthesis unit based on the character string.

The text-to-speech system of this embodiment includes a speech synthesis unit that synthesizes speech by concatenating pre-recorded speech fragments, and when the analysis unit analyzes that the imaged object is a character string, the output unit outputs the speech synthesized by the speech synthesis unit based on the character string.

The text-to-speech device of this embodiment includes a gripping unit, a window for looking into the image capture target, an imaging unit capable of imaging the image capture target while the image capture target is being looked into through the window, an analysis unit that analyzes image data captured by the imaging unit, and an output unit that outputs audio based on the analysis results of the analysis unit.

The text-to-speech device of this embodiment includes a detection unit that detects the distance to the object on which the image capture target is written, and a correction unit that corrects the imaging range of the imaging unit based on the distance detected by the detection unit so that the image capture target within the field of view through the window can be captured.

The information processing device of this embodiment includes a collection unit that collects image data obtained by capturing an image of an object, an analysis unit that analyzes the interests of the user who captured the image of the object based on the image data collected by the collection unit, and a provision unit that provides the analysis results of the analysis unit.

The information processing device of this embodiment includes a first analysis unit that analyzes the field of the image subject based on the image data collected by the collection unit, and the analysis unit analyzes the user's interests based on the analysis results of the first analysis unit collected each time a first predetermined period of time is reached.

In the information processing device of this embodiment, the analysis unit analyzes a first index related to the user's interests based on the number of subjects captured for each field analyzed by the first analysis unit.

The information processing device of this embodiment includes an identification unit that identifies changes in the first indicator analyzed by the analysis unit for each first predetermined period, and the analysis unit analyzes the user's type of interests in accordance with the changes in the first indicator identified by the identification unit.

In the information processing device of this embodiment, the analysis unit analyzes a second index related to the user's interests based on changes in the number of subjects captured for each field analyzed by the first analysis unit for each first predetermined period.

In the information processing device of this embodiment, the analysis unit analyzes the third index related to the user's interests based on the field with the largest number of imaging subjects among the number of imaging subjects captured for each field analyzed by the first analysis unit.

The information processing device of this embodiment includes a second analysis unit that analyzes the colors contained in the image subject based on the image data collected by the collection unit, and the analysis unit analyzes the user's color-related interests based on the analysis results of the second analysis unit collected each time a second predetermined period of time is reached.

The information processing device of this embodiment includes a third analysis unit that analyzes whether the imaged object is a string of characters or a figure based on the image data collected by the collection unit, a reading unit that reads out the string of characters if the third analysis unit analyzes that the imaged object is a string of characters, and a playback unit that plays sound related to the content of the figure if the third analysis unit analyzes that the imaged object is a figure, and the analysis unit analyzes the user's activity type based on the number of times the reading unit reads out the string and the number of times the playback unit plays it over a third predetermined period.

The information processing device of this embodiment includes an output unit that outputs audio based on the analysis results of the third analysis unit.

In the information processing device of this embodiment, the analysis unit analyzes the temporal changes in the interests of a group of users divided by at least one of age and region, based on the image data collected by the collection unit.

The imaging device of this embodiment includes a gripping unit, a window for looking into the imaging target, an imaging unit capable of imaging the imaging target while the imaging target is being looked into through the window, an analysis unit that analyzes the interests of the user who captured the imaging target based on image data captured and collected by the imaging unit, and a provision unit that provides the analysis results of the analysis unit.

The computer program of this embodiment causes a computer to execute the following process: collect image data obtained by capturing an image of an object, analyze the interests of the user who captured the image of the object based on the collected image data, and provide the analysis results.

REFERENCE SIGNS LIST 1 Home network 2 Communication network 10 Main unit 11, 201 Control unit 12 Communication unit 13, 205 Analysis unit 131, 206 Character string analysis unit 132, 207 Graphic analysis unit 14, 208 Voice synthesis unit 15, 209 Order estimation unit 16, 210 Memory unit 161, 211 BGM list 162, 212 Voice data list 17, 213 Microphone 18, 214 Speaker 19, 215 Emotion index calculation unit 21 Placement surface 22 Edge portion 23 Center portion 24 Restriction unit 25 Storage unit 26 Indicator light 30 Main unit 31 First communication unit 32 Second communication unit 33 Memory unit 331 BGM list 34 Microphone 35 Speaker 36 Control unit 50 Imaging device 51, 202 Imaging unit 52, 203 Distance sensor 53, 204 Correction unit 54 Memory 55 Processor 56 Communication unit 57 Speaker 69 Storage unit 70 Voice data list 100, 150 Terminal device 101, 151 Control unit 102 First communication unit 103 Second communication unit 152 Communication unit 104, 153 Display unit 105, 154 Operation unit 106, 162 Storage unit 163 Voice data list 164 Computer program 300 Server 301 Control unit 302 Communication unit 303 Analysis unit 304 Character string analysis unit 305 Figure analysis unit 306 Voice synthesis unit 307 Order estimation unit 308 Storage unit 309 Voice data list 310 Emotion index calculation unit 400 Server 401 Control unit 402 Communication unit 403, 155, 71 Analysis unit 404, 156, 72 Character string analysis unit 405, 157, 73 Graphic analysis unit 406, 158, 65 Order estimation unit 407, 159, 66 Speech synthesis unit 408, 160, 67 Sound reproduction unit 409, 161, 68 Analysis unit 410 Storage unit 411 Voice data list

Claims (12)

The image capturing device includes an imaging device and a main body device having a mounting surface on which an object having an image capturing target written thereon can be placed,
The imaging device is
A gripping portion;
a window for looking into the imaging target;
an imaging unit capable of imaging the imaging target in a state where the imaging target is viewed through the window;
a transmission unit that transmits image data obtained by capturing an image with the imaging unit to the main device,
The main body device includes:
a receiving unit that receives the image data;
an analysis unit that analyzes the image data received by the receiving unit;
an output unit that outputs a voice based on the analysis result of the analysis unit ;
an emotion index calculation unit that calculates an emotion index by performing a semantic analysis on the character string when the analysis unit analyzes the image data to determine that the image capture target is a character string;
Equipped with
The output unit
outputting background music according to the emotion index calculated by the emotion index calculation unit ;
Voice reading system. The placement surface is
It has a rectangular shape in plan view,
The mounting surface is inclined so that the height decreases from each of a pair of edge portions sandwiching the center portion of the mounting surface toward the center portion.
The text-to-speech system according to claim 1 . The main body device includes:
and a restricting portion for restricting movement of the object on another pair of edges of the placement surface along the inclined direction of the placement surface.
The text-to-speech system according to claim 1 or 2. The main body device includes:
a storage section for storing the imaging device is formed on the placement surface;
The text-to-speech system according to any one of claims 1 to 3. The imaging device is
a detection unit that detects the distance to the object;
a correction unit that corrects an imaging range of the imaging unit so that an imaging target within a field of view through the window unit can be imaged in accordance with the distance detected by the detection unit,
The text-to-speech system according to any one of claims 1 to 4. The analysis unit
Analyzing whether the imaged object is a character string or a picture based on the image data received by the receiving unit;
The output unit
When the analysis unit analyzes that the imaged object is a character string, a voice reading the character string is output.
The text-to-speech system according to any one of claims 1 to 5. The output unit
When the analysis unit analyzes that the imaging target is a figure, it outputs a sound related to the content of the figure.
The text-to-speech system according to claim 6. a reading order estimation unit that, when the analysis unit analyzes that the image capture target is a character string, estimates a reading order of the character string based on an arrangement of the character string;
The text-to-speech system according to any one of claims 6 to 7 . a speech synthesis unit that synthesizes speech using speech features of pre-recorded speech;
The output unit
When the analysis unit analyzes that the imaging target is a character string, the voice synthesis unit outputs a synthesized voice based on the character string.
The text-to-speech system according to any one of claims 6 to 8 . a speech synthesis unit that synthesizes speech by connecting pre-recorded speech fragments;
The output unit
When the analysis unit analyzes that the imaging target is a character string, the voice synthesis unit outputs a synthesized voice based on the character string.
The text-to-speech system according to any one of claims 6 to 8 . A gripping portion;
a window for looking into the imaging target;
an imaging unit capable of imaging the imaging target in a state where the imaging target is viewed through the window;
an analysis unit that analyzes image data captured by the imaging unit;
an output unit that outputs a voice based on the analysis result of the analysis unit ;
an emotion index calculation unit that calculates an emotion index by performing a semantic analysis on the character string when the analysis unit analyzes the image data to determine that the image capture target is a character string;
Equipped with
The output unit
outputting background music according to the emotion index calculated by the emotion index calculation unit ;
Voice reading device. a detection unit that detects the distance to the object on which the image is to be captured;
a correction unit that corrects an imaging range of the imaging unit so that an imaging target within a field of view through the window unit can be imaged in accordance with the distance detected by the detection unit,
The text-to-speech device according to claim 11 .