JP7592948B2 - Oral cavity function evaluation method, oral cavity function evaluation device, and program - Google Patents

Description

The present invention relates to an oral function evaluation method, an oral function evaluation device, and a program.

Oral diadochokinesis is a known method for evaluating oral function. In oral diadochokinesis, the oral function of a person is evaluated based on, for example, how many times the person can repeatedly utter a single syllable, such as "pa," "ta," or "ka," within 10 seconds.

When performing oral diadochokinesis, the assessor counts the number of "pa" sounds spoken, for example by marking dots on a piece of paper with a writing implement in time with the speech of the person being assessed. Cited Document 1 also discloses a technology that automatically counts the number of "pa" sounds by using voice recognition on the speech data spoken by the person being assessed.

JP 2013-235134 A

In conventional oral diadochokinesis, the person being assessed had to speak each syllable, such as "pa," "ta," and "ka," and the number of times each was counted. In other words, three speaking sessions and three counting sessions were required. This was a burden for both the person being assessed and the assessor.

The present invention was made in consideration of the above problems, and aims to make oral diadochokinesis easily possible.

An oral function evaluation method according to one embodiment is an oral function evaluation method executed by an oral function evaluation system, and includes an acquisition process for acquiring speech information in which a person being evaluated repeatedly speaks a predetermined phrase including a plurality of syllables, and an evaluation process for evaluating the speech based on the speech information.

According to one embodiment, oral diadochokinesis can be easily performed.

FIG. 1 is a diagram illustrating an example of the configuration of an oral cavity function evaluation system. FIG. 2 illustrates an example of a hardware configuration of an information processing device. FIG. 2 is a diagram illustrating an example of a functional configuration of an oral cavity function evaluation apparatus. FIG. 11 is a diagram showing an example of evaluation result information. 13 is a flowchart illustrating an example of processing executed by the oral cavity function evaluation system. FIG. 11 is a diagram illustrating an example of voice information. FIG. 13 is a diagram showing an example of an evaluation result display screen.

Each embodiment of the present invention will be described below with reference to the accompanying drawings. Note that in the description of the specification and drawings relating to each embodiment, components having substantially the same functional configuration are designated by the same reference numerals, and redundant description will be omitted.

<Configuration of oral function evaluation system>
First, an overview of the oral function evaluation system (hereinafter referred to as the "evaluation system") according to this embodiment will be described. The evaluation system according to this embodiment is an information processing system for performing oral diadochokinesis. Oral diadochokinesis is a test for evaluating the oral function of a person being evaluated by having the person being evaluated repeatedly utter syllables such as "pa,""ta," and "ka," and observing the person's speech. Oral diadochokinesis is performed, for example, in medical institutions, nursing homes, rehabilitation facilities, and at home.

In this embodiment, the person being evaluated repeatedly speaks a predetermined phrase that includes three or more syllables from among "pa," "ta," "ka," and "ra." The phrase may be a set of three syllables from among "pa," "ta," "ka," and "ra" arranged one by one in any order, or a set of four syllables from among "pa," "ta," "ka," and "ra" arranged one by one in any order. The phrase may also include syllables other than "pa," "ta," "ka," and "ra."

In the following, an example will be described in which the phrase is "pataka." That is, in this embodiment, the person being evaluated repeatedly speaks the three-syllable phrase "pataka." However, as described above, the phrase is not limited to "pataka."

In the following, the person being evaluated will repeatedly utter a predetermined phrase ten times. That is, in this embodiment, the person being evaluated will utter "patakapatakapatakapatakapatakapatakapatakapatakapatakapataka." However, the number of times the person being evaluated utters the predetermined phrase can be set arbitrarily. The person being evaluated may also repeatedly utter the predetermined phrase for a predetermined period of time (e.g., 10 seconds).

FIG. 1 is a diagram showing an example of the configuration of an evaluation system according to this embodiment. As shown in FIG. 1, the evaluation system according to this embodiment includes an oral function evaluation device 1 (hereinafter referred to as "evaluation device 1") and a user terminal 2, which are communicatively connected to each other via a network N. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination of these. In the example of FIG. 1, the evaluation system includes one evaluation device 1 and one user terminal 2, but may include multiple of each.

The evaluation device 1 is an information processing device that evaluates the oral function of the person being evaluated based on audio information 121 in which the person being evaluated repeatedly speaks phrases. More specifically, the evaluation device 1 evaluates the speech by calculating the measured values of one or more evaluation items related to speech based on the audio information 121 and evaluating the speech, thereby evaluating the oral function of the person being evaluated. The evaluation items include, for example, but are not limited to, speech speed, speech rhythm, breathing and pronunciation during speech. The evaluation device 1 is, for example, but is not limited to, a PC (Personal Computer), a smartphone, a tablet terminal, a server device, or a microcomputer. The evaluation device 1 will be described in more detail below.

The user terminal 2 is an information processing device used by a user of the evaluation system. The user may be the person being evaluated, or a third party different from the person being evaluated. In the following, an example will be described in which the user is a third party different from the person being evaluated. The user uses the user terminal 2 to acquire voice information 121 of the person being evaluated and transmit it to the evaluation device 1, and receives evaluation result information 123 from the evaluation device 1 to display the evaluation result. The user terminal 2 is, for example, a PC, a smartphone, or a tablet terminal, but is not limited to these.

<Hardware configuration of information processing device>
Next, a description will be given of the hardware configuration of the information processing device 100. Fig. 2 is a diagram showing an example of the hardware configuration of the information processing device 100. As shown in Fig. 2, the information processing device 100 includes a processor 101, a memory 102, a storage 103, a communication I/F 104, an input/output I/F 105, and a drive device 106, which are connected to each other via a bus B.

The processor 101 controls each component of the information processing device 100 and realizes the functions of the information processing device 100 by expanding into the memory 102 and executing various programs including an OS (Operating System) stored in the storage 103. The processor 101 is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), or a combination of these.

The memory 102 is, for example, a read only memory (ROM), a random access memory (RAM), or a combination of these. The ROM is, for example, a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a combination of these. The RAM is, for example, a dynamic RAM (DRAM), a static RAM (SRAM), or a combination of these.

Storage 103 stores various programs and data, including the OS. Storage 103 is, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a storage class memory (SCM), or a combination of these.

The communication I/F 104 is an interface for connecting the information processing device 100 to an external device via the network N and controlling communication. The communication I/F 104 is, for example, an adapter conforming to Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), Ethernet (registered trademark), or optical communication, but is not limited to these.

The input/output I/F 105 is an interface for connecting an input device 107 and an output device 108 to the information processing device 100. The input device 107 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a camera, various sensors, an operation button, or a combination of these. The output device 108 is, for example, a display, a projector, a printer, a speaker, a vibrator, or a combination of these.

The drive device 106 reads and writes data from and to the disk media 109. The drive device 106 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or a combination of these. The disk media 109 is, for example, a CD (Compact Disc), a DVD (Digital Versatile Disc), a FD (Floppy Disk), an MO (Magneto-Optical disk), a BD (Blu-ray (registered trademark) Disc), or a combination of these.

In this embodiment, the program may be written into the memory 102 or storage 103 during the manufacturing stage of the information processing device 100, or may be provided to the information processing device 100 via the network N, or may be provided to the information processing device 100 via a non-transitory computer-readable recording medium such as disk media 109.

<Functional configuration of oral cavity function evaluation device 1>
Next, a description will be given of the functional configuration of the evaluation device 1. Fig. 3 is a diagram showing an example of the functional configuration of the evaluation device 1. As shown in Fig. 3, the evaluation device 1 includes a communication unit 11, a storage unit 12, and a control unit 13.

The communication unit 11 is realized by the communication I/F 104. The communication unit 11 transmits and receives information to and from the user terminal 2 via the network N. The communication unit 11 transmits voice information 121 of the person being evaluated to the evaluation device 1 and receives evaluation result information 123 from the evaluation device 1.

The memory unit 12 is realized by the memory 102 and the storage 103. The memory unit 12 stores voice information 121, text information 122, evaluation result information 123, evaluation information 124, and advice information 125.

The audio information 121 is audio information in which the person being evaluated repeatedly speaks a specific phrase. In this embodiment, the audio information 121 is audio information in which the person being evaluated repeatedly speaks "pataca" ten times. Note that the audio information 121 may be audio information in which the person being evaluated repeatedly speaks a specific phrase a specific number of times. The audio information 121 may also be audio information in which the person being evaluated repeatedly speaks a specific phrase for a specific period of time.

Text information 122 is information indicating text generated from speech information 121 by speech recognition. If the person being evaluated correctly speaks "patakapataka...", text information 122 will be information indicating the text "patakapataka...".

The evaluation result information 123 is information that indicates the evaluation result of the oral function of the person being evaluated by the evaluation device 1. The evaluation result information 123 is stored in association with the audio information 121.

Figure 4 is a diagram showing an example of evaluation result information 123. The evaluation result information 123 in Figure 4 includes the following information items: "evaluation item," "measurement target," "measurement value," "score," "evaluation," and "advice."

"Evaluation items" are evaluation items for speech and oral function. In the example of Figure 4, the "evaluation items" include "speed," "rhythm," "breathing," "pronunciation (pa)," "pronunciation (ta)," "pronunciation (ka)," and "overall."

"Speed" is an evaluation item that evaluates the speed of speech. By evaluating the speed of speech, the smoothness of the mouth and tongue movements of the person being evaluated can be evaluated.

"Rhythm" is an evaluation item that evaluates the rhythm of speech. By evaluating the "rhythm" of speech, the endurance of the muscles around the mouth of the person being evaluated can be evaluated.

"Breathing" is an evaluation item that evaluates breathing while speaking. By evaluating breathing while speaking, the lung capacity of the person being evaluated can be evaluated.

"Pronunciation (pa)" is an evaluation item that evaluates the pronunciation of the syllable "pa." By evaluating the pronunciation of "pa," the strength of the person being evaluated's lips can be evaluated.

"Pronunciation (ta)" is an evaluation item that evaluates the pronunciation of the syllable "ta." By evaluating the pronunciation of "ta," the strength of the front of the tongue of the person being evaluated can be evaluated.

"Pronunciation (ka)" is an evaluation item that evaluates the pronunciation of the syllable "ka." By evaluating the pronunciation of "ka," the strength of the back of the tongue of the person being evaluated can be evaluated.

"Overall" is an evaluation item that evaluates oral function. "Overall" is an overall evaluation of the subject's oral function based on the evaluation items for each speech utterance.

"Measurement object" is the measurement object for evaluating the evaluation items. "Measurement object" includes "time (s)", "stability (%)", "number of breaths (times)", and "number of correct answers (times)".

"Time (s)" is the measurement of the evaluation item "speed," and is the time it takes to repeat "pataca" 10 times. The shorter the "time (s)," the smoother the mouth and tongue movements are, and the higher the oral function is evaluated.

"Stability (%)" is the measurement of the evaluation item "rhythm," and is the stability of the rhythm when "pataca" is spoken 10 times. "Stability (%)" takes a value between 0 and 100, and the more stable the rhythm of the speech, the higher the value. A higher "stability (%)" indicates greater endurance of the muscles around the mouth, and oral function is evaluated highly.

"Number of breaths" is the measurement of the evaluation item "breathing," and is the number of breaths taken when "pataka" is spoken 10 times. The fewer the "number of breaths," the greater the lung capacity, and the higher the oral function is evaluated.

The "number of correct answers (times)" is the measurement target for the evaluation items "pronunciation (pa)," "pronunciation (ta)," and "pronunciation (ka)," and is the number of times that "pa," "ta," and "ka" were correctly pronounced when "pata-ka" was pronounced 10 times. The "number of correct answers (times)" takes a value between 0 and 10, and the more accurate the pronunciation, the higher the number. The more "number of correct answers (times)" for "pronunciation (pa)" is, the stronger the power of the lips are, and the higher the oral function is evaluated. The more "number of correct answers (times)" for "pronunciation (ta)" is, the stronger the power of the front of the tongue is, and the higher the oral function is evaluated. The more "number of correct answers (times)" for "pronunciation (ka)" is, the stronger the power of the back of the tongue is, and the higher the oral function is evaluated.

The "measurement value" is the value of the "measurement object" calculated based on the audio information 121 and the text information 122. In the example of FIG. 4, the measurement value of "speed" is "15.42", the measurement value of "rhythm" is "21", the measurement value of "breathing" is "9", the measurement value of "pronunciation (pa)" is "5", the measurement value of "pronunciation (ta)" is "7", and the measurement value of "pronunciation (ka)" is "9".

"Score" is the evaluation value (quantitative evaluation) of the "evaluation item" evaluated based on the "measurement value." In the example of Figure 4, the score for "speed" is "0," the score for "rhythm," the score for "breathing" is "0," the score for "pronunciation" is "21," and the "overall" score is "21." The "overall" score is the sum of the scores for each evaluation item of speech. The "speech" score is the sum of the number of correct answers for "speech (pa)," "speech (ta)," and "speech (ka)."

"Evaluation" is a qualitative evaluation of the "evaluation item" based on the "measurement value" or "score." In the example of Figure 4, the evaluation of "Pronunciation (pa)" is "The pronunciation is disturbed," the evaluation of "Pronunciation (ta)" is "The pronunciation is sometimes disturbed," the evaluation of "Pronunciation (ka)" is "Your pronunciation is good!", and the evaluation of "Overall" is "Your pronunciation seems good!".

"Advice" is advice for an "evaluation item" that is provided based on the "measurements" or "scores." In the example of Figure 4, the "Overall" advice is "It's taking a while to finish speaking..."

Note that the evaluation result information 123 is not limited to the above example. The evaluation result information 123 may not include some of the above information items, or may include information items other than those described above. For example, the evaluation result information 123 may include evaluation items other than those described above. Furthermore, the measurement targets of the evaluation items are not limited to the above example.

Evaluation information 124 is text information that indicates a qualitative evaluation of the "evaluation item." Evaluation information 124 is stored in association with a "measurement value" or a "score."

Advice information 125 is text information indicating advice for an "evaluation item." Advice information 125 is stored in association with a "measurement value" or a "score."

The control unit 13 is realized by the processor 101 reading and executing a program from the memory 102 and working in cooperation with other hardware configurations. The control unit 13 controls the overall operation of the evaluation device 1. The control unit 13 includes an acquisition unit 131, a generation unit 132, and an evaluation unit 133.

The acquisition unit 131 acquires the voice information 121 of the person being evaluated from the user terminal 2. The acquisition unit 131 stores the acquired voice information 121 in the storage unit 12.

The generation unit 132 generates text information 122 from the voice information 121 by voice recognition. If the person being evaluated correctly utters "patakapataka...", the generation unit 132 generates text information 122 indicating the text "patakapataka...". The generation unit 132 may generate the text information 122 by voice recognition processing using, for example, an acoustic model, a language model, a pronunciation dictionary, and the like. The generation unit 132 may also generate the text information 122 from the voice information 121 by using an AI model that converts voice to text. The generation unit 132 stores the generated text information 122 in the storage unit 12.

The evaluation unit 133 evaluates the speech and oral function of the person being evaluated based on the audio information 121 and the text information 122. The evaluation of speech and oral function here includes the calculation of measurement values, the calculation of scores, the selection of an evaluation, and the selection of advice for each evaluation item. The evaluation method used by the evaluation unit 133 will be described in detail later.

The functional configuration of the evaluation device 1 is not limited to the above example. For example, the evaluation device 1 may have some of the functional configurations described above, and the user terminal 2 may have the rest. The evaluation device 1 may also have functional configurations other than those described above. Each functional configuration of the evaluation device 1 may be realized by software, as described above, or by hardware such as an IC chip, a SoC (System on Chip), an LSI (Large Scale Integration), or a microcomputer.

<Processing Executed by the Oral Function Evaluation System>
Next, a process executed by the evaluation system according to the present embodiment will be described with reference to a flowchart shown in FIG.

(Step S101)
First, the user asks the person to be evaluated to repeatedly speak a predetermined phrase, and the user terminal 2 acquires the speech information (step S101). Here, speech information in which the person to be evaluated repeatedly speaks "pataca" ten times is acquired. The user terminal 2 may acquire video information including the speech information instead of the speech information.

When the user acquires the voice information, the user operates the user terminal 2 to associate the acquired voice information with the information of the person being evaluated and transmit the information from the user terminal 2 to the evaluation device 1. The user may also transmit the voice information of the person being evaluated that has been stored in advance on the user terminal 2 to the evaluation device 1.

(Step S102)
When the acquisition unit 131 of the evaluation device 1 receives voice information from the user terminal 2, it acquires the received voice information as voice information 121 and stores it in the memory unit 12 in association with the information of the person being evaluated (step S102).

(Step S103)
When the voice information 121 is stored in the storage unit 12, the generation unit 132 generates text information 122 from the stored voice information 121 by voice recognition, and stores the text information 122 in the storage unit 12 in association with the voice information 121 (step S103). If the person being evaluated correctly utters "patakapataka...", the text information 122 will be information indicating the text "patakapataka...".

(Step S104)
When the voice information 121 and the text information 122 are saved, the evaluation unit 133 evaluates the speech and oral function of the person to be evaluated based on the voice information 121 and the text information 122, and stores the evaluation result information 123 in the storage unit 12 in association with the voice information 121 (step S104). The evaluation unit 133 transmits the stored evaluation result information 123 to the user terminal 2 in association with the voice information 121.

Here, FIG. 6 is a diagram showing a schematic example of the audio information 121. In the example of FIG. 6, the horizontal axis is time, and the vertical axis is amplitude. The audio information 121 in FIG. 6 includes waveforms corresponding to 10 "patakas." Note that the actual audio information 121 also includes other information such as frequency. Below, the evaluation methods for the five evaluation items of "speed," "rhythm," "breathing," "pronunciation," and "overall" will be explained.

(1) Method of Evaluating "Speed" When the subject repeatedly utters a predetermined phrase a predetermined number of times, the evaluation unit 133 calculates the time required for the subject to repeatedly utter the predetermined phrase a predetermined number of times as the "measured value (required time)" of "speed" based on the voice information 121. In the example of Fig. 6, the evaluation unit 133 calculates the time required to repeatedly utter "pata ka" ten times, that is, the time T from the start time t1 of the waveform of the first "pa" to the end time t2 of the waveform of the tenth "ka", as the "measured value" of "speed".

Next, the evaluation unit 133 determines a "score" for the "speed" based on the "measurement value". The evaluation unit 133 may calculate a "score" for the "speed" based on the "measurement value" of the "speed". The evaluation unit 133 may also refer to a correspondence table of "scores" and "measurement values" to select a "score" for the "speed" that corresponds to the "measurement value".

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "evaluations" included in the evaluation information 124 to determine the "evaluation" of "speed" that corresponds to the "score." Instead of the correspondence table between "scores" and "evaluations," a correspondence table between "measurements" and "evaluations" may be prepared. Also, if an "evaluation" of "speed" is not required, a correspondence table for "evaluations" does not need to be prepared.

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "advice" included in the advice information 125 to determine "advice" for "speed" that corresponds to the "score." Instead of a correspondence table between "scores" and "advice," a correspondence table between "measurements" and "advice" may be prepared. Also, if "advice" for "speed" is not required, a correspondence table for "advice" does not need to be prepared.

The evaluation unit 133 stores the "measured value", "score", "evaluation" and "advice" of "speed" thus determined in the storage unit 12 as evaluation result information 133. In the example of FIG. 4, the "measured value" of "speed" is "15.42", the "score" is "0", the "evaluation" is "-", and the "advice" is "-".

In addition, when the person being evaluated repeatedly speaks a specified phrase for a specified period of time, the evaluation unit 133 may calculate the number of times the person being evaluated repeatedly speaks the specified phrase within the specified period of time as a "measurement value" of "speed" based on the audio information 121.

(2) Evaluation method of "rhythm" When the subject repeatedly speaks a predetermined phrase a predetermined number of times, the evaluation unit 133 calculates the stability of the rhythm while the subject repeatedly speaks the predetermined phrase based on the voice information 121 as the "measurement value (stability)" of "rhythm". The stability of rhythm may be the smallness of the variation (such as variance) of the speech interval for each syllable ("pa", "ta", or "ka"), or the smallness of the variation of the speech interval of adjacent syllables. In addition, the stability of rhythm may be the number or the ratio of syllables included in a predetermined range based on the average value among the speech interval for each syllable or the speech interval of adjacent syllables. In either case, the more constant the speech interval, the higher the stability.

Next, the evaluation unit 133 determines a "score" for the "rhythm" based on the "measurement value." The evaluation unit 133 may calculate a "score" for the "rhythm" based on the "measurement value" of the "rhythm." The evaluation unit 133 may also refer to a correspondence table of "scores" and "measurement values" to select a "score" for the "rhythm" that corresponds to the "measurement value."

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "evaluations" included in the evaluation information 124 to determine the "evaluation" of the "rhythm" that corresponds to the "score." Instead of a correspondence table between "scores" and "evaluations," a correspondence table between "measurements" and "evaluations" may be prepared. Also, if an "evaluation" of the "rhythm" is not required, a correspondence table for "evaluations" does not need to be prepared.

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "advice" included in the advice information 125 to determine "advice" for "rhythm" that corresponds to the "score." Instead of a correspondence table between "scores" and "advice," a correspondence table between "measurements" and "advice" may be prepared. Furthermore, if "advice" for "rhythm" is not necessary, a correspondence table for "advice" does not need to be prepared.

The evaluation unit 133 stores the "measurement value," "score," "evaluation," and "advice" of "rhythm" thus determined in the storage unit 12 as evaluation result information 133. In the example of FIG. 4, the "measurement value" of "rhythm" is "21," the "score" is "0," the "evaluation" is "-," and the "advice" is "-."

In addition, when the person being evaluated repeatedly speaks a specified phrase for a specified period of time, the evaluation unit 133 may calculate the stability of the rhythm of the person being evaluated speaking the specified phrase for the specified period of time as a "measurement value" of "rhythm" based on the audio information 121.

(3) Method for Evaluating "Breathing" Based on the voice information 121, the evaluation unit 133 calculates the number of breaths taken by the subject while repeatedly uttering a predetermined phrase as the "measurement value (number of breaths)" of "breathing". In the example of FIG. 6, the evaluation unit 133 calculates the number of breaths taken while repeatedly uttering "pata ka" 10 times, that is, the number of breaths taken from the start time t1 of the waveform of the first "pa" to the end time t2 of the waveform of the tenth "ka", as the "measurement value" of "breathing". For example, the evaluation unit 133 detects a period in which the amplitude is equal to or less than a threshold value for a predetermined period or more in the voice information 121 as a period in which the subject took a breath. Note that the method for detecting a breath is not limited to this and is arbitrary.

Next, the evaluation unit 133 determines a "score" for "breathing" based on the "measurement value". The evaluation unit 133 may calculate a "score" for "breathing" based on the "measurement value" for "breathing". The evaluation unit 133 may also refer to a correspondence table of "scores" and "measurement values" to select a "score" for "breathing" that corresponds to the "measurement value".

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "evaluations" included in the evaluation information 124 to determine an "evaluation" of "breathing" that corresponds to a "score." Instead of a correspondence table between "scores" and "evaluations," a correspondence table between "measurements" and "evaluations" may be prepared. Also, if an "evaluation" of "breathing" is not required, a correspondence table for "evaluations" does not need to be prepared.

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "advice" included in the advice information 125 to determine "advice" for "breathing" that corresponds to the "score." Instead of a correspondence table between "scores" and "advice," a correspondence table between "measurements" and "advice" may be prepared. Furthermore, if "advice" for "breathing" is not necessary, a correspondence table for "advice" does not need to be prepared.

The evaluation unit 133 stores the thus determined "measurement value," "score," "evaluation," and "advice" for "breathing" in the storage unit 12 as evaluation result information 123. In the example of FIG. 4, the "measurement value" for "breathing" is "9," the "score" is "0," the "evaluation" is "-," and the "advice" is "-."

In addition, when the person being evaluated repeatedly speaks a specified phrase for a specified period of time, the evaluation unit 133 may calculate, based on the audio information 121, the number of breaths taken by the person being evaluated while repeatedly speaking the specified phrase for the specified period of time as a "measurement value" of "breathing."

(4) Method of Evaluating "Pronunciation" When the person being evaluated repeatedly speaks a predetermined phrase a predetermined number of times, the evaluation unit 133 calculates the number of times that the person being evaluated correctly pronounces each syllable while repeatedly speaking the predetermined phrase a predetermined number of times as a "measurement value (number of correct answers)" of "pronunciation" based on the text information 122. In the example of Fig. 6, the evaluation unit 133 calculates the number of times that the person being evaluated correctly pronounces "pa", "ta", and "ka" while repeatedly speaking "pataka" 10 times as the "measurement values" of "pronunciation (pa)", "pronunciation (ta)", and "pronunciation (ka)", respectively.

The number of times "pa" is pronounced correctly is the number of times that the syllable that should be pronounced "pa" in the phrase "pataka" is recognized as "pa" in the text information 122. This is because when "pa" is pronounced correctly, it is recognized as "pa" by voice recognition, whereas when "pa" is pronounced incorrectly, it is recognized as a syllable other than "pa" by voice recognition. The same applies to "ta" and "ka."

In the example of FIG. 6, in the text information 122, the audio information 121 is recognized as "patakahasakakatasapatakapakahatakapatakapakakakatakakataka." If the 10 syllables that should be pronounced as "pa" are extracted, they become "pa-ha-ka-pa-pa-ha-pa-pa-ka-ka," and 5 of the 10 syllables that should be pronounced as "pa" are recognized as "pa." Therefore, in the example of FIG. 6, the number of correct answers for "pronunciation (pa)" is 5. Similarly, the number of correct answers for "pronunciation (ta)" is 7, and the number of correct answers for "pronunciation (ka)" is 9.

Note that the "measurement value" of "pronunciation" may be the percentage of correct answers instead of the number of correct answers. In this case, the percentage of correct answers for correctly pronouncing "pa" is the number of correct answers for "pa" divided by the number of times "pata-ka" was repeated. The same applies to "ta" and "ka." In the example of Figure 6, the percentage of correct answers for "pronunciation (pa)" is 50%, the percentage of correct answers for "pronunciation (ta)" is 70%, and the percentage of correct answers for "pronunciation (ka)" is 90%.

Next, the evaluation unit 133 determines a "score" for "pronunciation" based on the "measurement value." The evaluation unit 133 may calculate a "score" for "pronunciation" based on the "measurement value" for "pronunciation." The evaluation unit 133 may also refer to a correspondence table of "scores" and "measurement values" to select a "score" for "pronunciation" that corresponds to the "measurement value." The "score" for "pronunciation" may be determined for each syllable, or may be determined as a total score for all syllables.

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "evaluations" included in the evaluation information 124 to determine the "evaluation" of "pronunciation" that corresponds to the "score." Instead of the correspondence table between "scores" and "evaluations," a correspondence table between "measurements" and "evaluations" may be prepared. Also, if an "evaluation" of "pronunciation" is not required, a correspondence table for "evaluations" does not need to be prepared.

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "advice" included in the advice information 125 to determine "advice" for "pronunciation" that corresponds to the "score." Instead of a correspondence table between "scores" and "advice," a correspondence table between "measurements" and "advice" may be prepared. Furthermore, if "advice" for "pronunciation" is not necessary, a correspondence table for "advice" does not need to be prepared.

The evaluation unit 133 stores the "measurement value," "score," "evaluation," and "advice" for "pronunciation" thus determined in the storage unit 12 as evaluation result information 123. In the example of FIG. 4, the "measurement value" for "pronunciation (pa)" is "5," the "evaluation" is "your pronunciation is disturbed," and the "advice" is "-." The "measurement value" for "pronunciation (ta)" is "7," the "evaluation" is "your pronunciation is sometimes disturbed," and the "advice" is "-." The "measurement value" for "pronunciation (ka)" is "9," the "evaluation" is "your pronunciation is good!", and the "advice" is "-." The "score" for "pronunciation" is "21."

(5) Method of Evaluating "Overall" The evaluation unit 133 determines the "score" of the "overall" based on the "score" of each "evaluation item" of the utterance. The evaluation unit 133 may calculate the "score" of the "overall" based on the "score" of each "evaluation item" of the utterance. The evaluation unit 133 may also select the "score" of the "overall" by referring to a correspondence table of the "score" of each "evaluation item" of the utterance and the "score" of the "overall". The evaluation unit 133 may determine the "score" of the "overall" based on the "measurement value" of each "evaluation item" of the utterance instead of the "score" of each "evaluation item" of the utterance.

Next, the evaluation unit 133 refers to a correspondence table between "scores" and "evaluations" included in the evaluation information 124 to determine an "overall" "evaluation" that corresponds to the "score." Instead of a correspondence table between "overall" "scores" and "evaluations," a correspondence table between "scores" or "measurements" and "evaluations" for each "evaluation item" of the utterance may be prepared. Also, if an "overall" "evaluation" is not necessary, a correspondence table for "evaluations" does not need to be prepared.

Furthermore, the evaluation unit 133 refers to a correspondence table between "scores" and "advice" included in the advice information 125 to determine the "overall" "advice" that corresponds to the "score." Instead of a correspondence table between "scores" and "advice," a correspondence table between "scores" or "measurements" for each "evaluation item" of the utterance and "advice" may be prepared. Also, if "overall" "advice" is not necessary, a correspondence table for "advice" may not be prepared.

The evaluation unit 133 stores the "total" "score", "evaluation" and "advice" thus determined in the storage unit 12 as evaluation result information 123. In the example of FIG. 4, the "total" "score" is "21", the "evaluation" is "Your pronunciation sounds good! ...", and the "advice" is "It's taking a while to finish speaking..."

Note that the "evaluation items," "measurement targets," "measurements," "scores," "evaluations," and "advice" for speech and oral function are not limited to the above examples. The evaluation result information 123 may not include some of the above information, or may include information other than the above.

(Step S106)
When the user terminal 2 receives the evaluation result information 123 from the evaluation device 1, the user terminal 2 displays the evaluation result indicated by the evaluation result information 123 on the evaluation result display screen (step S106).

Figure 7 is a diagram showing an example of an evaluation result display screen. The evaluation result display screen in Figure 7 displays the measured value of "speed" (15.42 seconds) and score (0/30 points), the measured value of "rhythm" (21%) and score (0/30 points), the measured value of "breathing" (9 times) and score (0/30 points), the score (5 points) and evaluation (your pronunciation is disturbed.) for "pronunciation (pa)", the score (7 points) and evaluation (your pronunciation is sometimes disturbed.) for "pronunciation (ta)", the score (9 points) and evaluation (your pronunciation is good!), and the score (21 points/30 points) and advice (your pronunciation is good! ...) for "overall".

By looking at this evaluation result display screen, the person being evaluated can learn the state of their own speech and oral function. Note that the evaluation results displayed on the evaluation result display screen are not limited to the above examples.

<Summary>
As described above, the evaluation system according to the present embodiment evaluates the speech and oral function of the person being evaluated based on the audio information of the person being evaluated repeatedly uttering a predetermined phrase including multiple syllables such as "pata-ka". This allows the person being evaluated to receive an evaluation of the speech of multiple syllables in one utterance. In addition, the evaluator can evaluate the speech of multiple syllables of the person being evaluated simply by acquiring the audio information of the person being evaluated's one utterance. In other words, when performing oral diadochokinesis, it is not necessary for the person being evaluated to utter and record each of the syllables such as "pa", "ta" and "ka", or for the evaluator to count the number of times each syllable is spoken. As a result, oral diadochokinesis can be easily performed by using this evaluation system.

The evaluation system can also automatically evaluate multiple evaluation items such as "speed," "rhythm," "breathing," "pronunciation," and "overall" based on audio information of repeated speech of specific phrases. This allows for a more detailed evaluation of the speech and oral function of the person being evaluated compared to when oral diadochokinesis is performed manually.

<Additional Notes>
The present embodiment includes the following disclosure.

(Appendix 1)
An oral function evaluation method executed by an oral function evaluation system, comprising:
An acquisition process for acquiring speech information in which the subject repeatedly speaks a predetermined phrase including a plurality of syllables;
an evaluation process for evaluating the speech based on the voice information;
A method for evaluating oral function comprising:

(Appendix 2)
The oral function evaluation method according to claim 1, wherein the phrase includes three or more syllables selected from the group consisting of pa, ta, ka, and ra.

(Appendix 3)
The oral function evaluation method according to claim 1, wherein the phrase is pataka.

(Appendix 4)
The oral function evaluation method according to claim 1, wherein the acquisition process acquires voice information in which the phrase is repeatedly spoken a predetermined number of times.

(Appendix 5)
The oral function evaluation method according to claim 1, wherein the acquisition process acquires audio information in which the phrase is repeatedly spoken for a predetermined period of time.

(Appendix 6)
The oral function evaluation method according to claim 1, wherein the evaluation process evaluates the speed of speech based on the voice information.

(Appendix 7)
The oral function evaluation method according to claim 1, wherein the evaluation process calculates the time required to repeat the phrase the predetermined number of times based on the voice information.

(Appendix 8)
The oral function evaluation method according to claim 1, wherein the evaluation process evaluates the rhythm of speech based on the audio information.

(Appendix 9)
The oral function evaluation method according to claim 1, wherein the evaluation process calculates the stability of speech rhythm based on the voice information.

(Appendix 10)
The oral function evaluation method according to claim 1, wherein the evaluation process evaluates breathing during speech based on the voice information.

(Appendix 11)
The oral function evaluation method according to claim 1, wherein the evaluation process calculates the number of breaths taken during speech based on the voice information.

(Appendix 12)
A generation process of generating text information from the voice information by voice recognition is further included.
The oral function evaluation method according to claim 1, wherein the evaluation process evaluates pronunciation based on the text information.

(Appendix 13)
A generation process of generating text information from the voice information by voice recognition is further included.
The oral function evaluation method according to claim 1, wherein the evaluation process calculates the number of correct pronunciations based on the text information.

(Appendix 14)
On the computer,
An acquisition process for acquiring speech information in which the subject repeatedly speaks a predetermined phrase including a plurality of syllables a predetermined number of times;
an evaluation process for evaluating the speech based on the voice information;
A program for executing an oral function evaluation method including the steps of:

(Appendix 15)
An acquisition unit that acquires speech information in which an assessee repeatedly speaks a predetermined phrase including a plurality of syllables a predetermined number of times;
an evaluation unit that evaluates the utterance based on the voice information;
An oral function evaluation system comprising:

The embodiments disclosed herein are illustrative in all respects and should not be considered restrictive. The scope of the present invention is indicated by the claims, not by the meaning described above, and is intended to include all modifications within the meaning and scope of the claims. Furthermore, the present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

1: Evaluation device 2: User terminal 11: Communication unit 12: Storage unit 13: Control unit 101: Processor 102: Memory 103: Storage 104: Communication I/F
105: Input/Output I/F
106: Drive device 107: Input device 108: Output device 109: Disk media 121: Audio information 122: Text information 123: Evaluation result information 124: Evaluation information 125: Advice information 131: Acquisition unit 132: Generation unit 133: Evaluation unit

Claims (12)

An oral function evaluation method executed by an oral function evaluation system, comprising:
An acquisition process for acquiring speech information in which the subject repeatedly speaks a predetermined phrase including a plurality of syllables;
an evaluation process of calculating the number of breaths taken during speech based on the voice information and evaluating breathing during speech;
A method for evaluating oral function comprising: The method for evaluating oral function according to claim 1 , wherein the phrase includes three or more syllables selected from the group consisting of pa, ta, ka, and ra. The method for evaluating oral function according to claim 1 , wherein the phrase is a pataka. The oral cavity function evaluation method according to claim 1 , wherein the acquisition process acquires speech information in which the phrase is repeatedly spoken a predetermined number of times. The oral cavity function evaluation method according to claim 1 , wherein the acquisition process acquires speech information in which the phrase is repeatedly spoken for a predetermined period of time. The evaluation process further includes a process of evaluating a speech rate based on the voice information.
The method for evaluating oral function according to claim 1 . the evaluation process further includes a process of calculating a time required to repeat the phrase a predetermined number of times based on the voice information.
The method for evaluating oral function according to claim 1 . The evaluation process further includes a process of calculating a stability of the rhythm of the speech based on the voice information.
The method for evaluating oral function according to claim 1 . A generation process of generating text information from the voice information by voice recognition is further included.
The evaluation process further includes a process of evaluating pronunciation based on the text information.
The method for evaluating oral function according to claim 1 . A generation process of generating text information from the voice information by voice recognition is further included.
The evaluation process further includes a process of calculating the number of correct pronunciations based on the text information.
The method for evaluating oral function according to claim 1 . On the computer,
An acquisition process for acquiring speech information in which the subject repeatedly speaks a predetermined phrase including a plurality of syllables a predetermined number of times;
an evaluation process of calculating the number of breaths taken during speech based on the voice information and evaluating breathing during speech;
A program for executing an oral function evaluation method including the steps of: An acquisition unit that acquires speech information in which an assessee repeatedly speaks a predetermined phrase including a plurality of syllables a predetermined number of times;
an evaluation unit that calculates the number of breaths taken during speech based on the voice information and evaluates breathing during speech;
An oral function evaluation system comprising: