WO2019203016A1 - Information processing device, information processing method, and program - Google Patents

Abstract

The present invention relates to an information processing device, an information processing method, and a program with which it is possible to improve speech recognition precision while minimizing the burden on a user. This information processing device comprises a presented information generation unit that generates presented information which is information presented to the user, and a presentation control unit that controls the presentation of the presented information to the user and induces the use of words and phrases for which speech recognition precision is high. The present invention can be applied to, for example, systems and devices that recognize user speech, interpret spoken content, and converse with the user.

Description

Information processing apparatus, information processing method, and program

The present technology relates to an information processing device, an information processing method, and a program, and more particularly, to an information processing device, an information processing method, and a program that improve the accuracy of speech recognition.

Conventionally, it has been proposed to improve speech recognition accuracy of each alphabet by adding a word (for example, a dot) set in advance before each alphabet and inputting the speech (for example, see Patent Document 1).

Japanese Patent No. 5596869

However, the invention described in Patent Document 1 can only be applied to the case where each alphabet is input by voice one by one. In addition, the user needs to know and follow the alphabet input method in advance, which increases the burden on the user.

The present technology has been made in view of such a situation, and is intended to improve voice recognition accuracy while suppressing the burden on the user.

An information processing apparatus according to one aspect of the present technology uses a presentation information generation unit that generates presentation information that is information to be presented to a user, and controls the presentation of the presentation information to the user, and uses a phrase with high voice recognition accuracy A presentation control unit for guiding

An information processing method according to one aspect of the present technology generates presentation information that is information to be presented to a user, controls presentation of the presentation information to the user, and induces use of a phrase with high voice recognition accuracy.

A program according to one aspect of the present technology generates presentation information that is information to be presented to a user, controls presentation of the presentation information to the user, and performs processing that induces use of a phrase with high voice recognition accuracy on a computer. Let it run.

In one aspect of the present technology, presentation information that is information to be presented to the user is generated, the presentation of the presentation information to the user is controlled, and the use of a phrase with high voice recognition accuracy is induced.

According to one aspect of the present technology, the voice recognition accuracy is improved while suppressing the burden on the user.

Note that the effects described here are not necessarily limited, and may be any of the effects described in the present disclosure.

It is a block diagram which shows the structural example of the dialogue system to which this technique is applied. It is a flowchart for demonstrating the dialogue process performed by a dialogue system. It is a figure which shows the 1st example of the presentation method of an option. It is a figure which shows the 2nd example of the presentation method of an option. It is a figure which shows the 3rd example of the presentation method of an option. It is a figure which shows the 4th example of the presentation method of an option. It is a figure which shows the 5th example of the presentation method of an option. It is a figure which shows the 6th example of the presentation method of an option. It is a figure which shows the structural example of a computer.

Hereinafter, embodiments for carrying out the present technology will be described. The description will be made in the following order.
1. Embodiment 2. FIG. Modified example 2. Other

<< 1. Embodiment >>
<Configuration Example of Dialog System 11>
FIG. 1 is a block diagram illustrating a configuration example of an interactive system 11 to which the present technology is applied.

The dialogue system 11 is a system that performs dialogue with the user using at least one of visual information (for example, images) and auditory information (for example, voice). For example, the interactive system 11 includes various systems and devices (for example, interactive robots, smart speakers, and the like) having a user interface using voice recognition. The dialogue system 11 includes an input unit 21, an information processing unit 22, and an output unit 23.

The input unit 21 is used for inputting input data to the information processing unit 22. The input unit 21 includes a microphone 31 and a camera 32.

The microphone 31 collects surrounding sounds including the user's voice, and supplies the voice data indicating the collected voice to the voice recognition unit 41, the noise recognition unit 42, and the user recognition unit 43 of the information processing unit 22.

The camera 32 shoots the user and supplies image data indicating the obtained image to the voice recognition unit 41 and the user recognition unit 43 of the information processing unit 22.

The information processing unit 22 executes various processes for performing a dialog with the user. The information processing unit 22 includes a voice recognition unit 41, a noise recognition unit 42, a user recognition unit 43, an interpretation unit 44, a learning unit 45, a user information storage unit 46, a phrase information storage unit 47, and a presentation processing unit 48.

The voice recognition unit 41 performs a process for recognizing the voice emitted by the user based on the voice data from the microphone 31 and the image data from the camera 32. The voice recognition unit 41 supplies data indicating the result of voice recognition to the interpretation unit 44 and the learning unit 45.

The noise recognition unit 42 performs processing for recognizing noise around the dialog system 11 (or the user) based on the voice data from the microphone 31. The noise recognition unit 42 supplies data indicating the result of noise recognition to the presentation processing unit 48.

The user recognition unit 43 performs a user recognition process based on the audio data from the microphone 31 and the image data from the camera 32. The user recognition unit 43 supplies data indicating the user recognition result to the learning unit 45.

The interpretation unit 44 interprets the user's utterance content based on the speech recognition result and the phrase information stored in the phrase information storage unit 47. The interpretation unit 44 supplies data indicating the user's utterance content to the learning unit 45 and the presentation processing unit 48.

The learning unit 45 learns the pronunciation characteristics of the user recognized by the user recognition unit 43 based on the speech recognition result and the utterance content, and updates the pronunciation characteristic information indicating the user's pronunciation characteristics.

The user information storage unit 46 stores user information (for example, pronunciation characteristic information, profile, etc.) related to each user who uses the dialogue system 11.

The phrase information storage unit 47 stores phrase information (for example, a dictionary, speech recognition accuracy of each phrase, etc.) related to the phrase used for the presentation information presented to the user.

The presentation processing unit 48 performs a process of presenting presentation information to the user. The presentation processing unit 48 includes a presentation information generation unit 61 and a presentation control unit 62.

The presentation information generation unit 61 generates presentation information based on the user's utterance content, the user information stored in the user information storage unit 46, and the phrase information stored in the phrase information storage unit 47. The presentation information generation unit 61 includes a presentation content setting unit 71 and a phrase selection unit 72.

The presentation content setting unit 71 sets the content of information to be presented to the user based on the user's utterance content and user information, and the phrase selection result by the phrase selection unit 72, and generates presentation information indicating the set content To do. The presentation content setting unit 71 supplies the presentation information to the presentation control unit 62.

The phrase selection unit 72 selects a phrase to be used for the presentation information based on the user information and the phrase information.

The presentation control unit 62 controls the presentation of presentation information to the user, and induces the use of words with high speech recognition accuracy and the suppression of the use of words with low speech recognition accuracy, as will be described later. For example, the presentation control unit 62 controls the display of the image indicating the presentation information by generating image data for visually presenting the presentation information and supplying the image data to the display 81 of the output unit 23. In addition, the presentation control unit 62 generates voice data for aural presentation of the presentation information and supplies it to the speaker 82 of the output unit 23 to control the output of voice indicating the presentation information.

The output unit 23 is used for outputting presentation information. The output unit 23 includes a display 81 and a speaker 82.

The display 81 displays an image based on the image data from the presentation control unit 62.

Speaker 82 outputs audio based on audio data from presentation control unit 62.

<Interaction processing>
Next, the dialogue process executed by the dialogue system 11 will be described with reference to the flowchart of FIG.

This process is started when, for example, the power of the dialog system 11 is turned on, and is ended when the power of the dialog system 11 is turned off.

In step S1, the dialogue system 11 starts acquiring input data.

Specifically, the microphone 31 collects surrounding sounds including the sounds emitted by the user, and supplies the sound data indicating the collected sounds to the sound recognition unit 41, the noise recognition unit 42, and the user recognition unit 43. To start.

The camera 32 starts photographing of the user and starts processing for supplying image data indicating the obtained image to the voice recognition unit 41 and the user recognition unit 43.

In step S2, the user recognition unit 43 starts user recognition. Specifically, the user recognition unit 43 performs a user recognition process based on the image data and the sound data, and starts a process of supplying data indicating the recognition result to the learning unit 45.

For the user recognition process, for example, any method can be used according to required accuracy, processing speed, and the like.

In step S3, the voice recognition unit 41 starts voice recognition. Specifically, the voice recognition unit 41 performs a process of recognizing a voice uttered by the user based on the voice data, and starts a process of supplying data indicating the recognition result to the interpretation unit 44 and the learning unit 45.

For voice recognition, for example, any method can be used according to required accuracy, processing speed, and the like. Further, for example, the voice recognition unit 41 may perform voice recognition using not only voice data but also image data (for example, a user's mouth shape) as necessary.

In step S4, the noise recognition unit 42 starts noise recognition. Specifically, the noise recognizing unit 42 performs processing for recognizing noise around the interactive system 11 (or the user) based on the voice data and supplying data indicating the recognition result to the presentation processing unit 48. Start. For example, voices other than the user's voice that is the target of voice recognition (for example, other person's voice, environmental sound, etc.) are recognized as noise.

For noise recognition, any method can be used depending on, for example, required accuracy and processing speed.

In step S5, the interpretation unit 44 starts interpretation of the user's utterance content. Specifically, the interpretation unit 44 performs a process of interpreting the content (meaning) spoken by the user based on the recognition result of the voice uttered by the user and the phrase information stored in the phrase information storage unit 47. Start. In addition, the interpretation unit 44 starts a process of supplying data indicating the interpreted utterance content to the learning unit 45 and the presentation processing unit 48.

It should be noted that any method can be used as the method for interpreting the utterance content depending on, for example, required accuracy and processing speed.

In step S6, the presentation information generation unit 61 generates presentation information for the user's utterance content. For example, when the presentation content setting unit 71 determines that a response is required for the user's utterance content, the content of information to be presented to the user (for example, response content) is set, and the presentation information indicating the set content Is generated. At this time, the phrase selection unit 72, as necessary, the user's pronunciation characteristics stored in the user information storage unit 46, the speech recognition accuracy of each phrase stored in the phrase information storage unit 47, and noise recognition. Based on the recognition result of ambient noise by the unit 42, a word / phrase to be used for the presentation information is selected. The presentation content setting unit 71 uses the phrase selected by the phrase selection unit 72 as the presentation information. The presentation content setting unit 71 supplies the generated presentation information to the presentation control unit 62.

An example of a method for generating presentation information will be described later.

In step S7, the dialogue system 11 presents presentation information. Specifically, the presentation control unit 62 generates at least one of image data and audio data for presenting presentation information to the user.

The presentation control unit 62 supplies the image data to the display 81 when the image data is generated. The display 81 displays an image indicating presentation information based on the image data. Thereby, the presentation information is visually presented to the user.

In addition, when the presentation control unit 62 generates voice data, the presentation control unit 62 supplies the voice data to the speaker 82. The speaker 82 outputs a sound indicating the presentation information based on the sound data. Thereby, presentation information is auditorily presented to the user.

An example of the presentation information presentation method will be described later.

In step S8, the learning unit 45 learns the pronunciation characteristics of the user.

For example, the learning unit 45 determines whether the speech recognition result is correct based on the content of the user's utterance. For example, when the user's utterance content is a negative reaction such as “different” or “not”, the learning unit 45 recognizes a speech of a phrase uttered by the user before presenting the presentation information that caused the negative reaction. It is determined that there is an error in the result. On the other hand, for example, when the user is responding normally to the presentation information, it is determined that the speech recognition result of the phrase issued by the user before the presentation information is presented is correct.

And the learning part 45 learns a user's pronunciation characteristic based on the correctness of the speech recognition result. For example, the learning unit 45 learns, for each user, a phrase or pronunciation that the voice recognition unit 41 is good at (high recognition accuracy) and a phrase or pronunciation that the voice recognition unit 41 is not good at (low recognition accuracy).

For example, the learning unit 45 determines that the speech recognition unit 41 is not good at recognizing the word / phrase of the user when the failure of the speech recognition for the same word / phrase is repeated for the user to be learned. For example, a case where the pronunciation of the word of the user is special or a case where the voice recognition unit 41 and the pronunciation of the word of the user are incompatible is assumed. In addition, for example, when the speech recognition success for the same word is repeated for the user, the learning unit 45 determines that the speech recognition unit 41 is good at recognizing the word of the user.

Further, for example, the learning unit 45 learns the pronunciation of the user who is not good at the voice recognition unit 41 (for example, the pronunciation of a line) based on the tendency of words and phrases that the voice recognition unit 41 is not good at.

The learning unit 45 updates the user's pronunciation characteristic information stored in the user information storage unit 46 based on the learning result.

Note that the timing for learning the pronunciation characteristics of the user is not limited to this example. For example, you may make it learn after the dialog with a user is over.

Thereafter, the process returns to step S6, and the processes after step S6 are executed.

Here, an example of presentation information and a presentation method will be described.

場合 When people talk, the same words are not always used. For example, in general, a person tends to follow a phrase used by the other party. For example, people tend to match words and phrases used by the other party in order to make the conversation smooth, or use words that are in sight unconsciously.

Therefore, for example, the presentation information generation unit 61 uses the person's tendency to use a word / phrase (hereinafter referred to as a high recognition word / phrase) with high recognition accuracy (voice recognition accuracy) of the voice recognition unit 41 for the user. Presentation information to be guided. In addition, for example, the presentation information generation unit 61 generates presentation information that guides the user to suppress the use of words (hereinafter referred to as low recognition words / phrases) with low recognition accuracy of the voice recognition unit 41.

The high recognition phrase and the low recognition phrase may be determined individually based on the recognition accuracy of the speech recognition unit 41, or may be relative based on the recognition accuracy relationship of the speech recognition unit 41 between the phrases. Sometimes it is decided. In the former case, for example, a phrase whose recognition accuracy of the speech recognition unit 41 is equal to or higher than a predetermined first threshold is classified as a high recognition phrase, and a phrase that is less than a second threshold and smaller than the first threshold is classified as a low recognition phrase. Is done. In the latter case, for example, of the two phrases, the phrase with higher recognition accuracy of the speech recognition unit 41 is classified as a high recognition phrase, and the phrase with lower recognition accuracy of the speech recognition unit 41 is classified as a low recognition phrase. Is done.

For example, the phrase selection unit 72 increases the priority used for the presentation information for a phrase with a higher recognition accuracy of the voice recognition unit 41, and decreases the priority for the presentation information for a phrase with a lower recognition accuracy of the voice recognition unit 41. Thereby, in the presentation information, the usage frequency of the high-priority words increases, and the usage frequency of the low-priority words decreases.

For example, the phrase selecting unit 72 selects a phrase having a higher priority when there are a plurality of usable phrases (for example, phrases having the same meaning). Further, for example, the phrase selection unit 72 replaces a low recognition phrase with a high recognition phrase having the same meaning, adds a high recognition phrase to the low recognition phrase, or selects a high recognition phrase as a phrase to be presented together with the low recognition phrase. . The presentation content setting unit 71 sets the presentation content using the phrase selected by the phrase selection unit 72, and generates presentation information indicating the set presentation content.

Thereby, since the high recognition word / phrase is preferentially presented to the user, the user is unconsciously guided to use the high recognition word / phrase. On the other hand, since the presentation of the low recognition phrase is suppressed, the user is unconsciously guided to suppress the use of the low recognition phrase. As a result, the recognition accuracy of the voice uttered by the user is improved.

Note that the priority of each word may be fixed regardless of the user and surrounding conditions, or may be dynamically changed according to the user and surrounding conditions.

For example, the phrase selection unit 72 sets the priority of each phrase based on the speech recognition accuracy of each phrase stored in the phrase information storage unit 47 without considering the user and surrounding circumstances. Thereby, the priority of each word is fixed. For example, when the speech recognition accuracy of each word is appropriately updated based on past recognition results, the priority of each word changes when viewed in a long span.

On the other hand, for example, the phrase selection unit 72 dynamically changes the priority of each phrase in consideration of the user and surrounding conditions in addition to the voice recognition accuracy of each phrase.

For example, depending on the user's pronunciation characteristics (for example, pronunciation habit), the voice recognition accuracy may differ between users even for the same word or phrase. Therefore, the phrase selection unit 72 adjusts the speech recognition accuracy of each phrase based on the pronunciation characteristics of the user stored in the user information storage unit 46, and prioritizes each phrase based on the adjusted speech recognition accuracy. Set the degree.

Also, for example, voice recognition accuracy may change even for the same word or phrase due to ambient noise. For example, in general, a short phrase is more likely to be buried in noise than a long phrase, and therefore, it is more susceptible to voice recognition accuracy due to noise. For example, when noise increases, generally speaking, a short word / phrase has a higher rate of decrease in speech recognition accuracy than a long word / phrase. In addition, for example, when another person is talking about a number around the user, the recognition accuracy regarding the number is lowered. Therefore, the phrase selection unit 72 adjusts the speech recognition accuracy of each phrase based on the recognition result of ambient noise, and sets the priority of each phrase based on the adjusted speech recognition accuracy.

Here, specific examples of the presentation information will be described with reference to FIGS. FIGS. 3 to 6 show an example in which presentation information including options such as “Inu”, “Saru”, “Kiji” is displayed on the display 81 and the user selects it.

For example, in the example of FIG. 3, numbers are displayed in front of each option as a phrase (hereinafter referred to as a selected term) used for selecting each option. As a result, the user utters the selected term phrases (“1”, “2”, “3”) in addition to the phrases (“Inu”, “Saru”, “Kiji”) representing each option. Choices can be selected.

Here, it is desirable to use a phrase with higher speech recognition accuracy as the selected term phrase. For example, when the alphabet has higher voice recognition accuracy than numbers, alphabets (“A”, “B”, “C”) are used for the selected term phrases instead of numbers as in the example of FIG. Thereby, the recognition rate (hereinafter referred to as the selection recognition rate) of options selected by the user by voice is improved.

In general, a short phrase (for example, a one-tone or two-tone phrase) tends to have lower speech recognition accuracy than a longer phrase. Therefore, for example, long words such as “Alpha”, “Bravo”, and “Charlie” may be used as the selected term phrases instead of short numbers and alphabets as in the example of FIG. Thereby, the selection recognition rate is improved.

As described above, speech recognition for short words is more susceptible to ambient noise than speech recognition for long words. Therefore, for example, the selected term phrase may be lengthened as the ambient noise level increases.

Furthermore, when a long word is used as the selected term, the space for displaying the selected term increases. For this reason, for example, the space for displaying the options may be reduced, or the options may be difficult to see. Further, depending on the characters used in the selected term phrase (for example, when the same character as the selected term phrase is included in the options), it may be difficult to distinguish the selected term phrase from the options. Further, depending on the type of characters used in the selected term phrase, it may be difficult to distinguish between the selected term phrases. Therefore, for example, instead of the selected term phrase, a symbol representing the selected term phrase (hereinafter referred to as a selection symbol) may be displayed together with the options. For example, an icon, a symbol, an image, or the like is used as the selection symbol.

In the example of FIG. 6, icons representing “star”, “moon”, and “sun” are used as selection symbols. Accordingly, the user can select an option by uttering “Hoshi”, “Tsuke”, and “Taiyo” which are words (selection term phrases) represented by the selection symbol in addition to the words representing the choices. it can.

Note that the phrase selection unit 72 selects, for example, a phrase having higher speech recognition accuracy than a phrase representing an option as a selected term phrase. Thereby, the selection recognition rate is improved as compared with the case where only the options are presented.

Also, for example, the presentation control unit 62 may control the presentation of the presentation information by a method that induces the use of the high recognition phrase and induces the suppression of the use of the low recognition phrase. Specifically, for example, the presentation control unit 62 is a mode represented by a highly recognized word / phrase, and controls to present each option in a different mode, and the user selects the option based on the word / phrase representing each mode. You may be able to do it.

For example, each option may be displayed using different display effects (for example, color, size, font, etc.), and the options may be selected by a word representing the display effect. For example, FIG. 7 shows an example in which each option and a selected term phrase are displayed in different colors because the difference in color is not shown because it is monochrome. Specifically, in FIG. 7, “A. Inu” is displayed in red, “B. Monkey” is displayed in blue, and “C. Kiji” is displayed in green. As a result, the user can select the choice by uttering the words (eg, “red”, “blue”, “green”) that indicate the color of each choice in addition to the phrase that represents each choice and the selected term. Can be selected.

Further, each option may be displayed at a different position so that the option can be selected by a word representing the display position. For example, in the example of FIG. 8, each option and the selected term phrase are displayed on the top, bottom, left, and right, respectively. As a result, the user utters a voice of a word (for example, “up”, “done”, “hidari”, “migi”) indicating the display position of each option, in addition to the word indicating each option and the selected word phrase. It is possible to select an option.

In addition, the presentation control unit 62 uses, for example, a phrase having higher speech recognition accuracy than a word representing an option as a word representing an aspect of presenting each option. In other words, the speech recognition accuracy is higher than that of a word representing an option. Control each option to be presented in a manner expressed by high phrases. Thereby, a selection recognition rate improves compared with the case where each choice is shown in the same mode.

In the example of FIG. 8, for example, the selection recognition rate can be further improved by using, for example, the user's gesture or the direction of the line of sight.

Further, in the examples of FIGS. 7 and 8, for example, it is possible to omit the presentation of the selected term phrase. That is, each option may be presented in a different manner without adding a selected term phrase to each option.

Also, for example, a phrase with higher voice recognition accuracy may be used as a phrase representing an option. For example, when the choices are “Keiyo Line”, “Keikyu Line”, and “Keio Line”, since the sounds between the choices are similar, the selection recognition rate may decrease. Thus, for example, the selection recognition rate can be improved by presenting the full names of each route such as “JR Keiyo Line”, “Keihin Express Line”, and “Keio Line” as options.

Furthermore, for example, when there are “1”, “2”, and “3” choices, it is assumed that each choice is short and the user only pronounces a numeric part. On the other hand, the selection recognition rate can be improved by, for example, presenting “one”, “two”, and “mitsu” as options.

In the above description, the case where the option is displayed on the display 81 is taken as an example. However, for example, when the option is presented by voice, the selection recognition rate is improved by using the selected term phrase similarly. Can do. For example, the selection recognition rate can be improved by outputting the selected term phrase and the choices by voice and allowing the user to input the voice of the selected term phrase.

As described above, words with higher voice recognition accuracy are used unconsciously by the user, and the voice recognition accuracy can be improved while suppressing the burden on the user. Thereby, for example, failure of voice recognition can be reduced, and a smooth dialogue with the user can be realized.

<< 2. Modification >>
Hereinafter, modifications of the above-described embodiment of the present technology will be described.

For example, in a use case where a certain standard expression (for example, “next”, “return”, etc.) is used, such as user interface navigation, a phrase with higher voice recognition accuracy is displayed on the display 81 as a typical expression. You may make it do. As a result, the user uses an expression with higher speech recognition accuracy for a typical expression.

Also, for example, the user may be guided to utter some words and phrases serving as pilot information, and the user's speech characteristics may be learned. Thereby, it becomes possible to learn a user's speech characteristic efficiently and in a short period of time.

Furthermore, for example, when the user's pronunciation habit is recognized to some extent, the pronunciation characteristic information of another user having the same habit is used until learning of the user's pronunciation characteristic is sufficiently advanced. Also good.

Further, for example, only one of preferential use of the high recognition phrase in the presentation information and suppression of use of the low recognition phrase in the presentation information may be performed. When only the former is performed, the user is mainly guided to use the high recognition phrase. When only the latter is performed, the user is mainly guided to suppress the use of low-recognition words.

Furthermore, for example, the pronunciation characteristic information of each user may be shared between different systems (for example, between a plurality of agents).

Further, the present technology is not limited to a scene where a dialogue with a user is performed, but can be applied to various scenes where a user's voice recognition is performed.

<< 3. Other >>
<Computer configuration example>
The series of processes described above can be executed by hardware or can be executed by software. When a series of processing is executed by software, a program constituting the software is installed in the computer. Here, the computer includes, for example, a general-purpose personal computer capable of executing various functions by installing a computer incorporated in dedicated hardware and various programs.

FIG. 9 is a block diagram showing an example of the hardware configuration of a computer that executes the above-described series of processing by a program.

In the computer 500, a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, and a RAM (Random Access Memory) 503 are connected to each other via a bus 504.

An input / output interface 505 is further connected to the bus 504. An input unit 506, an output unit 507, a recording unit 508, a communication unit 509, and a drive 510 are connected to the input / output interface 505.

The input unit 506 includes an input switch, a button, a microphone, an image sensor, and the like. The output unit 507 includes a display, a speaker, and the like. The recording unit 508 includes a hard disk, a nonvolatile memory, and the like. The communication unit 509 includes a network interface or the like. The drive 510 drives a removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

In the computer 500 configured as described above, the CPU 501 loads the program recorded in the recording unit 508 to the RAM 503 via the input / output interface 505 and the bus 504 and executes the program, for example. A series of processing is performed.

The program executed by the computer 500 (CPU 501) can be provided by being recorded on a removable medium 511 as a package medium, for example. The program can be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

In the computer 500, the program can be installed in the recording unit 508 via the input / output interface 505 by attaching the removable medium 511 to the drive 510. Further, the program can be received by the communication unit 509 via a wired or wireless transmission medium and installed in the recording unit 508. In addition, the program can be installed in the ROM 502 or the recording unit 508 in advance.

The program executed by the computer may be a program that is processed in time series in the order described in this specification, or in parallel or at a necessary timing such as when a call is made. It may be a program for processing.

Further, in this specification, the system means a set of a plurality of components (devices, modules (parts), etc.), and it does not matter whether all the components are in the same housing. Therefore, a plurality of devices housed in separate housings and connected via a network, and a single device housing a plurality of modules in one housing are all systems. .

Furthermore, embodiments of the present technology are not limited to the above-described embodiments, and various modifications can be made without departing from the gist of the present technology.

For example, the present technology can take a cloud computing configuration in which one function is shared by a plurality of devices via a network and is jointly processed.

Further, each step described in the above flowchart can be executed by one device or can be shared by a plurality of devices.

Further, when a plurality of processes are included in one step, the plurality of processes included in the one step can be executed by being shared by a plurality of apparatuses in addition to being executed by one apparatus.

<Combination example of configuration>
This technology can also take the following composition.

(1)
A presentation information generation unit that generates presentation information that is information to be presented to the user;
An information processing apparatus comprising: a presentation control unit that controls presentation of the presentation information to the user and guides use of a phrase with high voice recognition accuracy.
(2)
The information processing apparatus according to (1), wherein the presentation information generation unit generates the presentation information that induces use of a word with high voice recognition accuracy.
(3)
The information processing apparatus according to (2), wherein the presentation information generation unit selects a phrase to be used for the presentation information based on voice recognition accuracy of each phrase.
(4)
The information processing apparatus according to (3), wherein the presentation information generation unit preferentially uses words with high voice recognition accuracy for the presentation information.
(5)
The presentation information generation unit, when presenting options in the presentation information, selects a selected term phrase that is a phrase used for selection of the option based on the speech recognition accuracy of each phrase (3) or (4) The information processing apparatus described in 1.
(6)
The information processing apparatus according to (5), wherein the presentation information generation unit selects, as the selected term phrase, a phrase having higher speech recognition accuracy than a phrase representing the option.
(7)
The information processing apparatus according to (5) or (6), wherein the presentation information generation unit generates the presentation information that presents a symbol representing the selected term phrase together with the options.
(8)
The information processing apparatus according to any one of (3) to (7), wherein the presentation information generation unit further selects a word / phrase to be used for the presentation information based on the pronunciation characteristics of the user.
(9)
The information processing apparatus according to (8), further including a learning unit that learns the pronunciation characteristics of the user.
(10)
The information processing apparatus according to any one of (3) to (9), wherein the presentation information generation unit further selects a word / phrase to be used for the presentation information based on ambient noise.
(11)
The information processing apparatus according to (10), further including a noise recognition unit that recognizes the ambient noise.
(12)
The information processing apparatus according to any one of (1) to (11), wherein the presentation control unit controls presentation of the presentation information by a method for guiding the use of a word with high voice recognition accuracy.
(13)
When presenting options in the presentation information, the presentation control unit is an aspect represented by a phrase having high voice recognition accuracy, and controls the presentation of the presentation information so as to present the options in different aspects. The information processing apparatus according to (12).
(14)
The information processing apparatus according to (13), wherein the aspect is a display effect or a display position of the option.
(15)
The information processing apparatus according to (13) or (14), wherein the presentation control unit uses the aspect in which the word representing the aspect has higher voice recognition accuracy than the word representing the option.
(16)
The information processing apparatus according to any one of (1) to (15), wherein the presentation control unit controls presentation of the presentation information to the user and induces suppression of use of a phrase with low speech recognition accuracy.
(17)
The information processing apparatus according to any one of (1) to (16), further including a voice recognition unit that performs voice recognition of the user.
(18)
The information processing apparatus according to any one of (1) to (17), wherein the presentation information includes a response to the utterance content of the user.
(19)
Generate presentation information that is information to be presented to the user,
An information processing method for controlling the presentation of the presentation information to the user and guiding the use of a phrase with high speech recognition accuracy.
(20)
Generate presentation information that is information to be presented to the user,
A program for controlling a presentation of the presentation information to the user to induce the use of a word / phrase with high voice recognition accuracy.

In addition, the effect described in this specification is an illustration to the last, and is not limited, There may exist another effect.

11 dialogue system, 21 input unit, 22 information processing unit, 23 output unit, 31 microphone, 32 camera, 41 voice recognition unit, 42 noise recognition unit, 43 user recognition unit, 44 interpretation unit, 45 learning unit, 46 user information storage Section, 47 phrase information storage section, 48 presentation processing section, 61 presentation information generation section, 62 presentation control section, 71 presentation content setting section, 72 phrase selection section, 81 display, 82 speaker

Claims (20)

A presentation information generation unit that generates presentation information that is information to be presented to the user;
An information processing apparatus comprising: a presentation control unit that controls presentation of the presentation information to the user and guides use of a phrase with high voice recognition accuracy. The information processing apparatus according to claim 1, wherein the presentation information generation unit generates the presentation information that induces use of a word with high voice recognition accuracy. The information processing apparatus according to claim 2, wherein the presentation information generation unit selects a phrase to be used for the presentation information based on speech recognition accuracy of each phrase. The information processing apparatus according to claim 3, wherein the presentation information generation unit preferentially uses words with high voice recognition accuracy for the presentation information. 4. The information processing according to claim 3, wherein when presenting an option in the presenting information, the presenting information generating unit selects a selected term that is a term used for selecting the option based on speech recognition accuracy of each term. apparatus. The information processing apparatus according to claim 5, wherein the presentation information generation unit selects, as the selected term phrase, a phrase having higher speech recognition accuracy than a phrase representing the option. The information processing apparatus according to claim 5, wherein the presentation information generation unit generates the presentation information that presents a symbol representing the selected term phrase together with the options. The information processing apparatus according to claim 3, wherein the presentation information generation unit further selects a word / phrase to be used for the presentation information based on the pronunciation characteristics of the user. The information processing apparatus according to claim 8, further comprising a learning unit that learns the pronunciation characteristics of the user. The information processing apparatus according to claim 3, wherein the presentation information generation unit further selects a word / phrase to be used for the presentation information based on ambient noise. The information processing apparatus according to claim 10, further comprising a noise recognition unit that recognizes the ambient noise. The information processing apparatus according to claim 1, wherein the presentation control unit controls the presentation of the presentation information by a method for guiding the use of a phrase with high voice recognition accuracy. When presenting options in the presentation information, the presentation control unit is an aspect represented by a phrase having high voice recognition accuracy, and controls the presentation of the presentation information so as to present the options in different aspects. The information processing apparatus according to claim 12. The information processing apparatus according to claim 13, wherein the aspect is a display effect or a display position of the option. The information processing apparatus according to claim 13, wherein the presentation control unit uses the aspect in which the word representing the aspect has higher voice recognition accuracy than the word representing the option. The information processing apparatus according to claim 1, wherein the presentation control unit controls the presentation of the presentation information to the user and induces suppression of use of a phrase with low voice recognition accuracy. The information processing apparatus according to claim 1, further comprising a voice recognition unit that performs voice recognition of the user. The information processing apparatus according to claim 1, wherein the presentation information includes a response to the utterance content of the user. Generate presentation information that is information to be presented to the user,
An information processing method for controlling the presentation of the presentation information to the user and guiding the use of a phrase with high voice recognition accuracy. Generate presentation information that is information to be presented to the user,
A program for causing a computer to execute processing for controlling the presentation of the presentation information to the user and inducing use of a phrase with high speech recognition accuracy.

Images