JP6741387B2 - Audio output device - Google Patents

Description

The present invention relates to a voice output device that is mounted on a vehicle or the like and outputs a guidance voice or the like for navigation operation.

Conventionally, when a user misses the guidance voice output from a navigation device or the like, the guidance voice is again issued based on the operation status of the operation device by the user and the recognition result of the voice recognition device for the user's utterance. A sound output device that outputs the sound is known (for example, see Patent Document 1). In this voice output device, when the operation device is operated or a voice is uttered within a predetermined time after voice output, it is determined that the user has missed the voice output immediately before that, and the voice output is performed. Re-outputting.

JP, 2006-38705, A

By the way, in the above-described voice output device disclosed in Patent Document 1, a user who desires to re-output the guidance voice needs to perform a predetermined operation or utterance within a predetermined time after the missed guidance voice is output. , If the predetermined time is too short, the guidance voice according to the user's wishes may not be re-output. On the contrary, if the predetermined time is too long, the guidance voice not desired by the user may be re-output. There was a problem that the intention of the user might not be reflected. In particular, after the guidance voice is output, the timing at which the user who misses this guidance voice performs an operation or the like varies from user to user, and it is difficult to set an appropriate predetermined time for all users.

The present invention was created in view of the above circumstances, and an object thereof is to provide a voice output device capable of reliably outputting a missed guidance voice by reflecting the intention of the user. To provide.

In order to solve the above-mentioned problems, a voice output device of the present invention includes a guide voice output unit that outputs a guide voice, a voice recognition processing unit that performs a voice recognition process on a voice uttered by a user, and a voice. Based on the recognition result by the recognition processing means, if the content of the voice uttered by the user indicates a specific word indicating that the guide voice output immediately before has been missed, the guide voice output means On the other hand, it is provided with a guidance output instruction means for instructing the re-output of the guidance voice outputted immediately before. In particular, it is preferable that the above-mentioned specific word is one of a plurality of specific word candidates set assuming a voice that a user who misses the guidance voice will utter.

When the user misses the content of the output guidance voice and wants to hear it again, the user utters a voice of a specific word such as "what", "where", "one more time". Often. Therefore, by assuming such a specific word in advance and determining whether or not it matches with the voice recognition result, the intention of the user who wants to re-output the guidance voice is reflected and then missed. It is possible to reliably output the guidance voice again.

Further, the above-mentioned guidance voice output means can change the volume when outputting the guidance voice, and the guidance output instruction means instructs the guidance voice output means to increase the volume together with the re-output of the guidance voice. Is desirable. Further, the user further comprises audio means for outputting an audio sound that can be heard at the same time as the guide voice, and the guide output instructing means instructs the guide voice output means to re-output the guide voice and outputs the audio sound. Instruct the audio means to decrease the volume . As a result, by increasing the volume of the guidance voice and/or decreasing the volume of the audio sound and then re-outputting the guidance voice, the contents of the guidance voice can be surely transmitted to the user and missed again. Can be prevented.

Further, the guide voice output by the guide voice output means includes a first guide voice having a high importance and a second guide voice having a lower importance than the first guide voice. , The volume of the first guidance voice is increased and/or the volume of the audio sound is reduced when the first guidance voice is output again, and the second guidance is output when the second guidance voice is output again. It is desirable not to increase the volume of voice and decrease the volume of audio sound. This makes it possible to reliably prevent the important guidance voice from being missed again.

Further, it is preferable that the voice output device is mounted on a vehicle, the guide voice is output by the guide voice output means in the vehicle compartment, and the user is seated in a seat in the vehicle compartment. While the vehicle is running, it is thought that there will be more opportunities to miss the guidance voice content due to the effects of road noise, wind noise, rain noise, etc.However, even in such an environment, users who wish to re-output the guidance voice It is possible to surely re-output the missed guidance voice after determining the intention.

It is a figure which shows the structure of the vehicle-mounted apparatus of one embodiment. It is a figure which shows the relationship between the threshold value of a speech recognition process, and a score. 7 is a flow chart showing an operation procedure in the case where, after the guidance voice is output from the navigation processing unit, the user instructs the voice guidance to output the guidance voice.

Hereinafter, an on-vehicle device to which an audio output device of the present invention is applied will be described with reference to the drawings.

FIG. 1 is a diagram showing a configuration of an in-vehicle device according to an embodiment. As shown in FIG. 1, the vehicle-mounted device 1 includes a navigation processing unit 10, a TV tuner processing unit 14, a radio tuner processing unit 16, an AV processing unit 18, an operation unit 20, an input control unit 22, a display processing unit 24, and a display device. 26, a voice recognition processing unit 30, a microphone 32, a digital-analog converter (D/A) 40, a speaker 42, a control unit 50, and a hard disk device (HDD) 70.

The navigation processing unit 10 uses the map data stored in the hard disk device 70 to perform a navigation operation for guiding the travel of the vehicle in which the in-vehicle device 1 is mounted. Used in conjunction with the GPS (Global Positioning System) device 12 that detects the position of the vehicle, navigation operations that guide the travel of the vehicle include map display, route search/guidance, and search and display of nearby facilities. included. Further, the route guidance operation includes an operation of creating a guidance voice (route guidance) for guiding the traveling direction of the vehicle, changing the driving lane, etc. when passing through an intersection. In addition to the GPS 12, the own vehicle position may be detected by combining an autonomous navigation sensor such as a gyro sensor or a vehicle speed sensor.

The TV tuner processing unit 14 receives a broadcast signal such as a terrestrial digital broadcast and performs a process of reproducing video and audio. The radio tuner processing unit 16 receives a radio broadcast signal and reproduces sound. The AV processing unit 18 performs a process of reading out and reproducing music data or video data which is compressed and stored in the hard disk device 70. The music data and the video data may be those read from a CD or DVD using a disc reading device (not shown), or those received via a network. In addition, in the present embodiment, various audio and music output from each of the TV tuner processing unit 14, the radio tuner processing unit 16, and the AV processing unit 18 will be collectively described as “audio sound”.

The operation unit 20 is for receiving various operations by the user, and includes various switches and operation knobs. The input control unit 22 monitors the operation state of the operation unit 20 and detects the content input by the user.

The display processing unit 24 outputs video signals for displaying various operation screens, input screens, and the like, displays these screens on the display device 26, and also displays a video screen corresponding to the broadcast signal received by the TV tuner processing unit 14. A video signal for displaying a video screen or the like reproduced by the AV processor 18 is output to display these screens on the display device 26. The display device 26 is installed in the center front of the driver's seat and the passenger seat, and is configured by using, for example, a liquid crystal display device (LCD).

The voice recognition processing unit 30 compares the voice uttered by the user collected by the microphone 32 with each of a plurality of recognition words that are recognition candidates stored in the voice recognition dictionary, thereby performing the voice recognition process. I do. In the present embodiment, the voice uttered by the user is constantly collected, and the voice recognition process is performed on the voice from the beginning of the collected voice to the time when the utterance ends.

For example, consider a case where the user utters "one more time" and recognizes this content by performing voice recognition processing. When the first "mo" occurs, the recognition word "one more time" , The voice recognition process will fail. Similarly, at the time of uttering "another", "another", "another", etc., there is a large difference between these and the recognition word "another", so that the voice recognition process fails. When uttering "again", the difference between the recognition word "again" to be compared becomes small, and the voice recognition process succeeds.

In order to perform such processing, the concepts of "distance" and "score" are introduced. The distance indicates a similar distance between a voice as a comparison target and a recognition word. For example, as shown in FIG. 2, the maximum distance is set to "1000" as the largest similarity distance. The score S indicates the similarity distance between the actual input voice and the recognition word “again”. As described above, in the case where the user utters "one more time", the score at the start of utterance is 1000, and the score of the input voice gradually decreases as the utterance progresses. To do. Then, when the score of the input voice at the time when the utterance ends is less than the predetermined threshold Th, a recognition result that the content of the input voice matches the recognition word is obtained. In general, similar processing is performed in parallel for each of a plurality of recognition words, and finally one recognition word is extracted as a recognition result. If the score of the input voice at the time when the utterance ends is not less than the predetermined threshold Th (when there is no recognition word close to the input voice), it means that the voice recognition process has failed, and again. Processing such as prompting for voice input is performed.

By the way, considering the case where the user utters a voice having the same content as the recognition word stored in the voice recognition dictionary, the final score S should be a small value, and the threshold Th is set to a certain small value. However, it should be possible to recognize the content of the voice uttered by the user. However, in reality, road noise, wind noise, rain noise, audio sound, and the like are collected together with the voice uttered by the user, so that the final score S of the voice uttered by the user is quiet. It does not become as small as when collecting sound under the environment. In consideration of this point, the threshold Th for determining the success or failure of the voice recognition process cannot be set to a too small value. In other words, if the voice recognition process is performed using the threshold Th set in this way, the difference between the threshold Th and the score S is the case where the voice recognition process is successful. Is small, the surroundings of the user are environments where road noise, wind noise, rain sounds, audio sounds, etc. are large, and when the difference between the threshold Th and the score S is large, the surroundings of the user are large. Can be said to be a quiet environment with little road noise, wind noise, rain noise, and audio noise.

The user may operate the talk switch or the like to instruct the start and end of the utterance, and the voice recognition processing may be performed with the input voice during that period as the recognition target.

The digital-analog converter 40 converts the guide voice and the audio sound (digital data) generated by the processing of the navigation processing unit 10, the TV tuner processing unit 14, the radio tuner processing unit 16, and the AV processing unit 18 into an analog voice. It is converted into a signal and output from the speaker 42. Although an amplifier for amplifying a signal is actually connected between the digital-analog converter 40 and the speaker 42, this amplifier is omitted in FIG. Further, although there are as many combinations of the digital-analog converter 40 and the speaker 42 as there are reproduction channels, only one set is shown in FIG.

The control unit 50 is for controlling the entire vehicle-mounted device 1, and is realized by executing a predetermined program stored in a ROM, a RAM, or the like by the CPU. The control unit 50 includes a missed-arrival word determination unit 51, an important point determination unit 52, a surrounding situation determination unit 53, an audio volume change unit 54, a guide volume change unit 55, and a guide output instruction unit 56.

The missed-aloud thought word determination unit 51 determines whether or not the voice content obtained by the voice recognition processing by the voice recognition processing unit 30 matches the missed-loving thought word. For example, a plurality of specific words are set in advance as the missed thought words, and it is determined whether or not they match any one of the plurality of specific words. Specifically, "what", "where", "one more time", etc. are set as the specific word. Of course, these specific words need to be included in the recognition words that are the recognition candidates stored in the voice recognition dictionary used in the voice recognition processing by the voice recognition processing unit 30.

The important point determination unit 52 determines whether the output point of the guidance voice corresponds to the important point. In the present embodiment, attention is paid to the guidance voice output during the route guidance operation by the navigation processing unit 10, and the place on the travel route set as the place where the guidance voice is output corresponds to the important point. It is determined whether or not. In addition, this important point is a place where the user expects to hear the guidance voice (first guidance voice) that is highly important to the user without fail, and for example, at the next branch point. This includes a place where the user is notified by voice guidance that the vehicle will turn right or left, a place where the user is notified of a change in lane (lane guidance), and the like. On the other hand, the place where the user is notified to go straight at the next branch point, the place where the user is told to drive on the road for a while, and the like are used as guide voices (second These places are not included in the important points because it is considered that there is no problem even if you miss the (guidance voice).

The surrounding situation determination unit 53 determines the surrounding situation (environment) of the user who hears the guidance voice. As described above, whether or not the guidance voice is difficult to hear can be determined based on the relationship between the threshold Th and the score S during the voice recognition process. Specifically, when the voice recognition processing by the voice recognition processing unit 30 is successful, but the difference between the threshold Th and the score S is less than a predetermined value (for example, 30), road noise and wind noise of the vehicle, It is determined that the guidance voice is difficult to hear because the rain sound is loud or the output audio sound is loud. On the contrary, when the difference between the threshold Th and the score S is a predetermined value (for example, 30) or more, the road noise, wind noise, rain noise, etc. of the vehicle are small and the output audio sound is small (or It is determined that the guidance voice is in a state where it is easy to hear due to reasons such as (not being output).

The audio volume changing unit 54 instructs any one of the TV tuner processing unit 14, the radio tuner processing unit 16, and the AV processing unit 18 outputting the audio sound to reduce the volume of the audio sound. The guidance volume changing unit 55 instructs the navigation processing unit 10 to increase the volume of the guidance voice. The guidance output instructing unit 56 instructs the navigation processing unit 10 to output guidance voice.

The navigation processing unit 10 described above serves as a guidance voice output unit, the voice recognition processing unit 30 serves as a voice recognition processing unit, the audio volume changing unit 54, the guidance volume changing unit 55, and the guidance output instructing unit 56 serve as guidance output instructing means. The tuner processing unit 14, the radio tuner processing unit 16, and the AV processing unit 18 correspond to audio means, respectively.

The vehicle-mounted device 1 of the present embodiment has such a configuration, and the operation thereof will be described next. FIG. 3 is a flow chart showing an operation procedure in the case where the guidance voice is output from the navigation processing unit 10 and thereafter the guidance voice is output by the user.

First, the voice recognition processing unit 30 determines whether or not the voice recognition processing has succeeded on the voice uttered by the user (step 100). When the success is not reached (when the voice content cannot be recognized), a negative determination is made, and this determination is repeated.

When the voice recognition is successful (when the content of the voice can be recognized), a positive determination is made in the determination of step 100. Next, the missed-aloud word arrival determination unit 51 determines whether or not the content of the voice as the voice recognition result matches the missed-over miss word (step 102). For example, when the voice uttered by the user matches a specific word such as “what”, “where”, or “again”, an affirmative determination is made.

Next, the important point determination unit 52 determines whether or not the guidance voice output by the navigation processing unit 10 immediately before is related to the important point (step 104). If the point is an important point, a positive determination is made.

Next, the audio volume changing unit 54 sends an instruction to the TV tuner processing unit 14 or the like to reduce the volume of the audio sound, and the guide volume changing unit 55 sends an instruction to the navigation processing unit 10 to set the volume of the guide voice. After increasing the number, the guidance output instructing unit 56 sends an instruction to the navigation processing unit 10 to re-output the guidance voice (step 106).

When the re-output of the guide voice is completed, the audio volume changing unit 54 sends an instruction to the TV tuner processing unit 14 or the like to restore the volume of the audio sound, and the guide volume changing unit 55 gives an instruction to the navigation processing unit 10. The volume of the guide voice is returned to the original level (step 108). If no audio sound is output from the TV tuner processing unit 14 or the like, the instructions for reducing the volume of the audio sound in steps 106 and 108 are omitted. In this way, the re-output operation of the series of guidance voices is completed.

If the voice uttered by the user does not match a specific word such as "what", "where", "one more time", the user outputs voice guidance such as "route guidance" or "guidance". If a voice is issued, a negative determination is made in the determination at step 102.

Next, the surrounding situation determination unit 53 determines whether or not the situation in which the guidance voice is difficult to hear has occurred, specifically, the threshold value Th in the voice recognition process corresponding to the recognition word when the voice recognition process is successful. And the score S is less than 30 (Th-S<30) (step 110). If it is less than 30, an affirmative determination is made, the process proceeds to step 104, and the determination operation regarding important points and subsequent operations are repeated.

Further, when the output guidance voice does not relate to an important point and a negative determination is made in the determination of step 104, or the difference between the threshold Th and the score S during the voice recognition processing is 30 or more. If a negative determination is made in the determination of step 110, then the guidance output instructing unit 56 sends an instruction to the navigation processing unit 10, and under the same conditions as the previous time (decrease the volume of the audio sound or increase the volume of the guidance voice). The guidance voice is re-output (without performing) (step 112). In this way, the re-output operation of the series of guidance voices is completed. Although the guide voice output immediately before is re-outputted in step 112, the same guide voice is not re-outputted when the time has elapsed since the immediately preceding output time of the guide voice. Alternatively, a guidance voice having different contents may be output.

When the user misses the content of the output voice guidance and wants to hear it again, the user can use a specific word such as "what", "where", "one more time" that indicates the missed listening. Often speaks. Therefore, in the vehicle-mounted apparatus 1 of the present embodiment, such a specific word is assumed in advance to determine whether the voice recognition result matches or does not match the intention of the user who wants to re-output the guidance voice. After being reflected, it is possible to reliably re-output the missed guidance voice.

In addition, by increasing the volume of the guidance voice and/or decreasing the volume of the audio sound and then re-outputting the guidance voice, the contents of the guidance voice can be surely transmitted to the user, so that the user will not miss it again. It becomes possible to prevent it.

Further, when the guidance voice having a high degree of importance is to be reproduced, the volume of the guidance voice is increased and/or the volume of the audio sound is reduced, so that it is possible to reliably prevent the important guidance voice from being missed again. It becomes possible.

In addition, when the vehicle is running, it is considered that there will be more opportunities to miss the guidance voice content due to the effects of road noise, wind noise, rain noise, etc. Even in such an environment, it is desired to re-output the guidance voice. It is possible to reliably output the missed voice again after reflecting the user's intention.

The present invention is not limited to the above embodiment, and various modifications can be made within the scope of the gist of the present invention. For example, in the above-described embodiment, the determination regarding the important point is performed in step 104 of FIG. 3, but this determination is omitted, and the operation proceeds to the next step 106 regardless of whether or not the determination is regarding the important point. You may do so.

Further, in the above-described embodiment, the case where the user misses the guidance voice output during the navigation operation has been described, but the voice output other than the navigation operation (for example, the operation content of the AV processing unit 18 is The present invention can be applied to the case of re-outputting the guidance voice shown or a voice reading the contents of the received mail in the operation of receiving the mail or the like. Further, the present invention is not limited to the case of being mounted in a vehicle, and the present invention can be applied to a case of re-outputting a sound output from a device used indoors or outdoors outside the vehicle.

As described above, according to the present invention, a user who wishes to re-output the guidance voice by assuming in advance a specific word indicating that he/she has missed it and determining whether or not it matches the voice recognition result. It is possible to reliably re-output the missed guidance voice after reflecting the intention of the above.

1 In-vehicle device 10 Navigation processing unit 14 TV tuner processing unit 16 Radio tuner processing unit 18 AV processing unit 30 Speech recognition processing unit 32 Microphone 51 Missing hearing word determination unit 52 Important point determination unit 53 Surrounding situation determination unit 54 Audio volume change unit 55 guidance volume change unit 56 guidance output instruction unit

Claims (5)

Guide voice output means for outputting a guide voice,
Voice recognition processing means for performing voice recognition processing on the voice uttered by the user,
If the content of the voice uttered by the user indicates a specific word indicating that the guidance voice output immediately before is missed based on the recognition result by the voice recognition processing means, the guidance is given. Guidance output instruction means for instructing the voice output means to re-output the guidance voice outputted immediately before,
Audio means for outputting an audio sound that the user can hear at the same time as the guide voice,
Wherein the guidance output instruction means instructs the re-output of the guide voice to the guidance voice output means, characterized that you instruct the volume reduction of the audio sound to said audio means speech Output device. 2. The specific word is one of a plurality of specific word candidates set assuming a voice that a user who misses the guide voice will utter. Audio output device. The guide voice output means can change the volume when outputting the guide voice,
3. The voice output device according to claim 1, wherein the guidance output instruction unit instructs the guidance voice output unit to increase the volume together with the re-output of the guidance voice. The guide voice output by the guide voice output unit includes a first guide voice having a high importance and a second guide voice having a lower importance than the first guide voice,
When re-outputting the first guidance voice, the volume of the first guidance voice is increased and/or the volume of the audio sound is reduced, and when re-outputting the second guidance voice, The voice output device according to any one of claims 1 to 3, wherein the volume of the second guidance voice is not increased and the volume of the audio sound is not reduced. It is installed in the vehicle,
The guidance voice is output by the guidance voice output means in the vehicle interior,
User audio output device according to any one of claims 1 to 4, characterized in that seated on the seat of the passenger compartment.

Images