JPH0695828A - Voice input system - Google Patents

Abstract

PURPOSE:To agreeably utilize a voice input function by displaying visually constraint information at the time of utilizing a voice input of a voice input object sentence pattern, a voice recognition object word, etc., so as to be easily understandable in accordance with a state of a system. CONSTITUTION:In an applied data processing part 4, a processing is executed based on an input from a voice recognizing part 2, and a response of a result of processing, etc., to be presented to a user is outputted to a display control part 5. For instance, based on a partition of input information of a difference of a vocabulary, etc., requested by the applied data processing part 4, information of an internal state set in advance is outputted. In a voice input constraint information managing part 3, by this information, an internal state-continuous/ isolated utterance corresponding table is retrieved, and whether the present voice can be inputted in a continuous voice or isolated utterance is necessary, is outputted. Subsequently, in a display control part 5, this information and a result of processing from the applied data processing part 4 are outputted to a display part 6. In the display part 6, this information, especially whether the present continuous utterance is executed or the isolated utterance is necessary, is displayed visually so as to be easily understandable.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice input system using voice recognition in an information processing system having means for visually displaying the results of data processing such as editing, translation, calculation, drawing and copying.

[0002]

2. Description of the Related Art Conventionally, a voice input interface has been put into practical use in applications such as telephone inquiries and data input systems to computers. However, when the voice input method is difficult to understand or erroneous recognition occurs. Since it was difficult to understand how to correct the input information of, the user interface was not easy to use.

Further, in recent years, electronic computers are equipped with a plurality of input means (multimodal interface) such as a keyboard, a mouse, a microphone, an image scanner, and a pen input to enable various input methods. Therefore, some or all of the conventional input functions using a keyboard and a mouse are enabled by voice input using a microphone, and there is an increasing demand for a user-friendly multi-modal user interface that uses a keyboard, a mouse, and a microphone together. For example, there is an increasing demand for a user interface that allows not only mouse clicking on a button of a window system but also uttering characters displayed on the button to input.

However, when a beginner uses the above-described system that uses a keyboard, a mouse, and a microphone in combination, a voice input target sentence pattern, a voice recognition target word, continuous / isolated utterance, a specific / unspecified speaker target, and a voice recognition dictionary are created. Because there was no prior knowledge about the constraint information related to the use of voice input such as the voice data collection method for, the input method was not understood and the user was confused or made an input error. For example,
In the case of voice input using a microphone, only a pre-registered input word can be voice-recognized, so that the user needs to know the voice input target word in advance and input the voice.

Further, since a large amount of voice data is required to create a recognition dictionary for voice recognition, voice input may not be supported for all input targets displayed on the screen. For example, even if the same button item of the window system can be input and cannot be input by voice, the user knows in advance which button item can be input by voice and is displayed on the button item. It was necessary to utter the letters that were present. Especially,
Beginners were confused and made input mistakes without knowing which button items could be used for voice input. Even a skilled user had to remember a button item capable of voice input by himself or, otherwise, it was necessary to check by checking a table of words for voice input. Therefore, the interface is burdensome for the user and is not easy to use.

[0006]

As described above, in the conventional system using the voice input, the user has a voice input target sentence pattern, a voice recognition target word, continuous / isolated utterance, a specific / unspecific speaker target, a male / Female speakers, adult / child speakers,
Constraint information related to the use of voice input, such as voice input ON / OFF, was difficult to understand, which caused confusion or input error.

The present invention has been made to solve such a conventional problem, and an object thereof is to provide a voice input system capable of easily displaying constraint information regarding the use of voice input. is there.

[0008]

In order to achieve the above object, a voice input system according to the present invention has a voice input target sentence pattern, a voice recognition target word, continuous / isolated utterance, a specific / unspecified speaker target, a male / Female speakers, adult / child speakers,
A means for displaying constraint information related to a voice input usage pattern such as ON / OFF of voice input and a speech style in an easy-to-understand manner by visual information such as characters, figures, images, intensity of light, color difference, density, and texture. It is equipped with.

[0009]

According to the present invention, when the command execution, function selection, and data input are supported by voice input, the internal state of the current system is checked, and the voice input target sentence pattern and voice input target word in that state are checked. , Continuous / isolated utterance, specific / unspecified speaker target, recognition target speaker's gender and age, recognition performance, and other constraint information when using voice input, including characters, figures, images, intensity of light, and color Since the difference and texture are displayed in an easy-to-understand manner by controlling visual information such as texture, the user can understand at a glance the constraint conditions at the time of voice input and the utterance method.

Therefore, the user can comfortably use the voice input function without being confused about the restriction information related to the use of voice input or causing an input error, and realizes a human interface which is easy for a beginner to use. it can.

[0011]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a configuration diagram of a voice input system according to a first embodiment of the present invention. In the figure, a voice is converted into an electric signal through a voice input unit 1 and a voice recognition unit 2
Is input to. In the voice recognition unit 2, the input voice is
For example, it is converted into a digital signal having a sampling frequency of 12 kHz and a quantization bit number of 16 bits, and a characteristic parameter time series is obtained by frequency analysis by, for example, fast Fourier transform,
Furthermore, for example, the composite similarity method, HMM (Hidden Marcov Mode
Speech recognition is performed based on the method such as l) and the vocabulary or sentence with the highest likelihood is output to the application data processing unit as the recognition result.

The application data processing unit 4 is, for example, software or a system that supports operations such as translation, calculation, editing, drawing, copying, reservation, and automatic cash payment. The application data processing unit 4 processes based on the input from the voice recognition unit, then outputs a response such as a processing result to be presented to the user to the display control unit 5, and, for example, the vocabulary requested by the application data processing unit 4. The information on the internal state preset based on the division of the input information such as the difference between the voice input restriction information management unit 3
Output to. For example, in the airline ticket reservation system, when the input requested by the application data processing unit changes from the state of “destination” to the state of “departure time”, it changes to the internal state of inputting “departure time”. Is output to the voice input restriction information management unit 3.

The voice input restriction information management unit 3 uses, for example, Table 1 according to the change information of the internal state of the application data processing unit 4.
Such an internal state-continuous / isolated utterance correspondence table is searched, and it is determined whether it is possible to input the voice continuously by the utterance or whether it is necessary to utter the utterance at present, the voice recognition unit 2 and the display control unit 5.
Output to.

[0014]

[Table 1] The display control unit 5 outputs the processing result from the application data processing unit 4 and information indicating the distinction between continuous and isolated utterances to the display unit 6. The display unit 6 displays the information from the display control unit 5 on the screen, and particularly, visually displays whether the continuous utterance or the isolated utterance is required at present.

As an application example, a case where the application data processing unit 4 supports the reservation of airline tickets will be described. First, when the apparatus is started, the application data processing unit 4 outputs the information of the initial state to the voice input restriction information management unit 3 and the display information of the initial screen to the display control unit 5. The voice input restriction information management unit 3 searches the internal state-continuous / isolated utterance correspondence table shown in Table 1, and obtains information indicating that continuous utterance is possible in the initial state, from the voice recognition unit 2 and the display control unit. Output to 5. The display control unit 5 creates display data for visually displaying the display information from the application data processing unit 4 and the information indicating that continuous speech is possible from the voice input restriction information management unit 3, and outputs the display data to the display unit 6. As shown in Table 2, the display section 6 displays a reservation / cancel, a display for selecting a destination and a flight number, and a display indicating that continuous utterance is possible.

[0016]

[Table 2] The user can see at a glance that it is sufficient to continuously select the reservation or cancellation and speak the destination / flight number.

Next, when the user utters "Reserved New York" when he / she wants to book a flight to New York, the voice recognition unit 2 knows from the voice input restriction information management unit 3 that the user will continuously speak. The recognition is performed more accurately using a recognition method suitable for continuous utterance rather than isolation, and inputs such as “reservation” and “New York” are input to the application data processing unit 4. Application data processing unit 4
Then, as shown in FIG. 2, the internal state changes to a state in which the departure time of the airline ticket is designated, and similarly to the above, the information regarding the internal state of the time designated state shown in Table 2 is output to the voice input restriction information management unit. Then, the display information of the time designation screen is output to the display control unit 5. Then, the voice input restriction information management unit 3 and the display control unit 5 perform the same processing as described above, and the flight designation screen shown in Table 3 is displayed.

[0018]

[Table 3] Note that Table 3 shows an example of inputting an isolated utterance by leaving the voice of the month, day, hour, and minute blank (silent) for a predetermined time. However, it is possible to divide the voice by key input or clicking the mouse. May be.

As described above, by displaying on the screen whether the voice input can be continuously uttered or whether it is necessary to perform the isolated utterance, the user can understand the distinction between the continuous / isolated utterance methods of the voice at a glance. Therefore, it is possible to construct an easy-to-use interface without being confused about whether the continuous / isolated utterance method is appropriate or erroneous.

Next, a second embodiment of the present invention will be described. The configuration is the same as that of the first embodiment, but the voice input restriction information management unit is necessary because the recognition target vocabulary shown in Table 4 is accepted as an input instead of the internal state-continuous / isolated utterance correspondence table. It manages a recognition target vocabulary-utterance count correspondence table in which various utterance counts are set.

[0021]

[Table 4] The processing flow of the voice input unit 1 and the application data processing unit 4 is the same as in the first embodiment. The voice input restriction information management unit 3 refers to a recognition target vocabulary-speech count correspondence table as shown in Table 4, and determines the number of utterances necessary for the current recognition target vocabulary to be an input and the voice recognition unit 2 and display control. The speech recognition unit 2 outputs the vocabulary to the application data processing unit 4 as a recognition result when each vocabulary is continuously input by the number of times input by the voice input restriction information management unit 3. To do.

The application data processing unit 4 outputs a response such as a processing result to the display control unit 5, and outputs change information of the internal state to the voice input restriction information management unit 3. The display control unit 5 outputs to the display unit 6 the display information from the application data processing unit 4 and the information indicating the number of times of utterance of the input vocabulary input from the voice input restriction information management unit 3. In the display unit 6, the display information from the display control unit 5 is displayed on the screen, and in particular, the number of times the input vocabulary is currently uttered is visually displayed in an easy-to-understand manner.
For example, by uttering an input vocabulary that requires certainty as a user interface multiple times, a more stable interface can be realized. For example, as shown in Fig. 3, vocabulary that can be input with one utterance ("next screen")
Indicates that the vocabulary is surrounded by a single frame, and the vocabulary that needs to be uttered twice (“end”) is displayed by surrounding the vocabulary with a double frame. Is a user-friendly interface because the number of utterances of the input vocabulary can be understood at a glance.

In FIG. 3, the utterance is shown twice by a double frame. However, the display of characters, the frame, and the like are shaded, and when the tone is dark, it is instructed to speak loudly. You can also It is also possible to indicate the number of occurrences by other display methods such as displaying symbols or marks such as “☆” and “*” on the shoulders for the number of times of utterance.

It is also possible to intermittently output an audio signal such as a buzzer a plurality of times to specify the number of times of voice input repetition.

Next, a third embodiment will be described. Although the configuration is the same as that of the first embodiment, the voice input restriction information management unit 3 manages the number input method table as shown in Table 5 instead of the internal state-continuous / isolated utterance correspondence table.

[0026]

[Table 5] The processing flow of the voice input unit 1 and the application data processing unit 4 is the same as in the first embodiment.

The voice input restriction information management unit 3 refers to the number input method table as shown in Table 5 and outputs the utterance method for voice input of a plurality of digits to the voice recognition unit 2 and the display control unit 5. To do. For example, when the internal state of the application data processing unit 4 is a state in which the personal identification number is input, the numeral input method table shown in Table 5 is referred to, and a plurality of digits are entered from the upper digit "Ichi""D""San". ] The voice recognition unit 2 provides constraint information (individual utterances) regarding the utterance method of uttering using 11 types of voices of "Young", "Si", "Go", "Roku", "Shichi", "Nana", "Hachi", and "Kyu". Is output to the display control unit 5. For example, as shown in the example of Table 6, in the case of an individual occurrence, the user has to utter the number 8215, digit by digit, such as "Hachini Strawberry". If the internal state of the application data processing unit 4 is in the state of inputting a reservation number as shown in the example of Table 7, the numeral input method table is referred to and a plurality of digits including the number of digits are uttered. The constraint information (voices of a plurality of digits) regarding the utterance method is output to the voice recognition unit 2 and the display control unit 5. In this case, the user has to say the number 251 as "Nyakugojuichi". Similarly, acceptance of both can be visually indicated.

The voice recognition unit 2 selects and recognizes a voice recognition dictionary according to the constraint information relating to the number utterance method input from the voice input constraint information management unit 3 in the number recognition. For example, a voice recognition dictionary is selected and recognized by distinguishing between a case where a number is input by voice one digit at a time (individual utterance) and a case where a number is input by voice including a number of digits (utterance at a plurality of digits).
As a result, it is possible to reduce the ambiguity in the recognition of numbers and perform recognition, so that the recognition performance can be improved.

The application data processing unit 4 outputs a response such as a processing result to be presented to the user to the display control unit 5, and outputs the internal state change information to the voice input restriction information management unit 3.
The display control unit 5 outputs the information indicating the distinction to the display unit based on the display information from the application data processing unit 4 and the constraint information regarding the utterance method of the numeric input input from the voice input constraint information management unit 3. The display unit 6 displays the display information from the display control unit 5 on the screen, and particularly visually displays the constraint information regarding the number utterance method at present. For example, as shown in Table 6, in the state in which the personal identification number of the cash card is entered, a plurality of digits starting from the upper digit are "Ichi", "D", "San", "Yon", "Shi", "Go", and "Roku". It is displayed in an easy-to-understand manner that the utterance is made using 11 types of voices such as "shichi", "nana", "bee" and "kyu".

[0030]

[Table 6] Further, as shown in Table 7, it is displayed in an easy-to-understand manner that a plurality of digits including the number will be uttered when the reservation number is input.

[0031]

[Table 7] This allows the user to understand the utterance method when inputting numbers at a glance, making the interface easy to use,
Further, the recognition performance can be improved.

Next, a fourth embodiment will be described. FIG. 4 shows a block diagram of a voice input system according to a fourth embodiment of the present invention. In the first embodiment, the processing result of the application data processing unit 4 is not displayed but is output as voice, and the information indicating the distinction between continuous / isolated utterance, which is constraint information regarding voice input, is the same as in the first embodiment. It is displayed on the display unit 6. The flow of processing is the same as in the first embodiment, but the application data processing unit 4 outputs the processing result to the audio output unit 7 instead of the display control unit 5. As a result, it becomes possible to recognize the voice and confirm the response by telephone.

Next, a fifth embodiment will be described. FIG. 5 is a block diagram of a voice input system according to the fifth embodiment of the present invention.

The voice is converted into an electric signal through the voice input unit 1 and input to the voice recognition unit 2. In the voice recognition unit 2,
The input voice, for example, a sampling frequency of 12kHz, 1
It is converted into a digital signal having a quantization bit number of 6 bits, and a characteristic parameter time series is obtained by frequency analysis by, for example, a fast Fourier transform.
Speech recognition is performed based on a method such as HMM (hidden marcov model) and the vocabulary or sentence with the highest likelihood is output to the application data processing unit 4 as a recognition result.

The input information control unit 8 converts the recognition result from the voice recognition unit 2 and the input information from the keyboard 9 and the mouse 10 into input data and control signals to the application data processing unit 4, and the application data processing unit 4 Output to. The application data processing unit 4 is software or a system that supports work such as translation, calculation, editing, drawing, and copying. The application data processing unit 4 processes the input data and control signals from the input information control unit 8 as input, and displays information such as screens and sentences to be displayed to the user in the current state on the display control unit 5.
Then, the change information of the internal state of the application data processing unit 4 is output to the voice input restriction information management unit 3.

In the voice input restriction information management unit 3, as shown in FIG. 6, the internal state-voice input target vocabulary correspondence table as shown in Table 8 is used by using the input change information of the internal state of the application data processing unit 4. The current application data processing unit 4
The vocabulary for speech recognition in the internal state of is detected.

[0037]

[Table 8] Next, the current voice input target vocabulary is output to the voice recognition unit 2, and the current internal state information of the application data processing unit 4 is output to the display control unit 5.

The display control unit 5 holds an input target display management table as shown in Table 9, for example.

[0039]

[Table 9] The input target display management table is a screen displayed according to the internal state of the application data processing unit 4, a vocabulary displayed on the screen, information on which medium can input the vocabulary, and the vocabulary displayed. Holds information such as the target. For example, for the vocabulary “edit” in the input target display management table of Table 9, it is possible to input with the mouse or voice on the screen in the initial state, and hold the information that it is displayed on the button item. ing.
In the display control unit 5, when converting the information related to the screen display from the application data processing unit 4 into the screen display data, the current application data processing unit 4 input from the voice input restriction information management unit 3 in the input target management table described above. Display the color, shape, background color, surrounding figure, font, etc. of the display target (for example, button item) that uses voice as the input medium on the internal state of the screen separately from the display target that does not use voice as the input medium. And outputs the data to the display unit 6. The display unit 6 displays the input screen display data to the user, such as a CRT display.

The case where the application data processing unit 4 supports the text editing work will be described. First, when the apparatus is started, the application data processing unit 4 outputs the information of the initial state to the voice input restriction information management unit 3 and the display information of the initial screen to the display control unit 5. The voice input restriction information management unit 3 searches the internal state-speech input target vocabulary correspondence table shown in Table 8, and the speech recognition target vocabulary "edit", "layout", "output", "end" in the initial state. Is output to the voice recognition unit 2 and the display control unit 5.

In the display control unit 5, in the vocabulary of the initial screen of the input target display management table as shown in Table 9, "edit", "layout", "output" input from the voice input restriction information management unit 3 is entered. , "And" end "are corrected so that the voice item of the input medium can be input (OK). Next, referring to the input target display management table, on the mouse buttons of “Edit”, “Layout”, “Output”, and “End” which are the display targets for which audio can be input in the input medium of the initial screen. The characters are displayed in red, the "document name" that is the other display target is controlled to be displayed in black, and the display data is output to the display unit. As shown in FIG. 7, four buttons “Edit”, “Layout”, and
The characters "output" and "end" are displayed in red, and can be distinguished from other characters in black at a glance. The user can understand that the vocabulary displayed in red characters can be input by voice and the vocabulary displayed in black can be input by the mouse or the keyboard.

In this initial state, when the user selects the document name with the mouse, the document name is input.
Is output to. Next, when "edit" is uttered, the recognition result "edit" in the voice recognition unit 2 is output to the input information control unit 8. The input information control unit 8 outputs to the application data processing unit 4 the same control signal as when the selected document name and the edit button item are clicked with the mouse. Then, the application data processing unit 4 changes the internal state to the editing state, outputs the information of the editing state to the voice input restriction information management unit 3 and outputs the display information of the editing screen to the display control unit 5 as described above. . The voice input restriction information management unit 3 and the display control unit 5 perform the same processing as described above, and the text editing screen shown in FIG. 8 is displayed.

In this way, by displaying the display color of the vocabulary supporting the voice input on the screen in distinction from the vocabulary not supporting the voice input, the user can understand the vocabulary that can be voice input at a glance. Therefore, it is possible to construct an easy-to-use interface without being confused by not knowing which vocabulary can be input by voice or uttering a vocabulary that is not the target of voice recognition. Furthermore, the voice recognition unit 2 can narrow down the current input target vocabulary and collate it with the voice standard pattern, so that the recognition performance is improved.

Further, the vocabulary frequently used may be inputted by voice, and the vocabulary rarely used may be inputted by button.

Next, a sixth embodiment will be described. In the fifth embodiment, the background texture is distinguished not by the display color of the voice input target vocabulary and the non-target vocabulary. The flow of processing is the same as in the fourth embodiment. For example, as shown in FIG. 9, a button item capable of voice input is displayed in an easy-to-understand manner by the texture.

Next, a seventh embodiment will be described. Figure 10
FIG. 13 is a configuration diagram of a voice input system according to a seventh embodiment of the present invention.

A voice recognition dictionary creating section 12 is added to the configuration of the fifth embodiment. The voice recognition dictionary creating unit 12 manages voice data of an unspecified user and voice data input by a specific user, which the system holds in advance, and creates a voice recognition dictionary using the managed voice data. Speech recognition unit 2
The recognition dictionary is output to. Furthermore, the voice recognition dictionary creation unit 1
In 2, the number of data of the unspecified user and the number of data of the specific user in the voice data for which the recognition dictionary is created are output to the voice input restriction information management unit 3.

The processing flow of the input information control unit 8 and the application data processing unit 4 is the same as that of the fifth embodiment, but the voice input restriction information management unit 3 creates a recognition dictionary from the voice recognition dictionary creation unit 12. Based on the information of the voice data, the specific / non-specific dictionary creation data number table shown in Table 10 is created.

[0049]

[Table 10] Further, the voice input restriction information management unit 3 refers to the specific / non-specific dictionary creation data number table shown in Table 10 to inform the display control unit 5 of the current internal state information of the application data processing unit 4 and each recognition target. The number of voice data of the unspecified speaker and the number of voice data of the user used when creating the vocabulary recognition dictionary are output to the display control unit 5, and the current recognition target vocabulary is output to the voice recognition unit 2.

The display control unit 5 searches the input target management table, and the larger the (the number of voice data of the user) / (the number of voice data of the unspecified speaker) of the vocabulary to be the current voice input target, the larger The display data is output to the display unit 6 by controlling the display color of the button item displaying the vocabulary to be dark. In the display unit 6, for example, FIG.
As shown in, the “copy” of (the number of voice data of the user) / (the number of voice data of the unspecified speaker) = 1.2 is displayed in a dark color, and (the number of voice data of the user) / (the unspecified talk) “Paste” in which the number of voice data of a person) = 0.1 is displayed in a light color. With this, the user can understand at a glance how much the recognition dictionary of each vocabulary is trained by his / her own voice. Therefore, if the user does not have good recognition performance for a vocabulary for which the training rate of the dictionary by his / her own voice is small, the recognition performance can be improved by recreating the dictionary by adding his / her own voice data as a means of improving the recognition performance. I understand.

It is also possible to assign red and blue colors to the two users and change the display color according to the frequency of use of each user. For example, if "red" is assigned to the user A and "blue" is assigned to the user B, the vocabulary frequently used by the user A is changed to red and the vocabulary frequently used by the user B is changed to blue. Then, the red vocabulary is set so that the user A can easily recognize it, while the blue vocabulary is set so that the user B can easily recognize it. This makes it possible to build a more user-friendly interface.

Next, the eighth embodiment will be described. 12
FIG. 13 is a configuration diagram of a voice input system according to an eighth embodiment of the present invention.

In addition to the configuration of the fifth embodiment, the voice data management unit 1
3 is added. The voice data management unit 13 manages voice data input or registered in advance by a specific user, utterance contents (vocabulary) of those voice data, and information on the internal state of the application data processing unit 4 capable of inputting the vocabulary. is doing. The voice data management unit 13 outputs the voice data to the voice recognition unit 2 and further manages the internal state of the application data processing unit 4 where the vocabulary can be input and the utterance content (vocabulary) of the voice data for voice input restriction information management. Output to the part 3. In the voice input restriction information management unit 3, the internal state as shown in Table 8-
With reference to the voice input target vocabulary correspondence table, the vocabulary to be recognized in the internal state of the application data processing unit 4 input from the voice data managing unit 13 is output to the voice recognizing unit 2 and recognized by the voice recognizing unit 2. The recognition rate for each vocabulary is calculated by comparing the result with the utterance content input from the voice data management unit 13, and a recognition rate table as shown in Table 11 is created.

[Table 11] Further, the voice input from the voice input unit 1 to the voice recognition unit 2 is processed in the same manner as in the fifth embodiment, and the processing flow of the input information control unit 8 and the applied data management unit 4 is also the same as in the fifth embodiment. is there. The voice input restriction information management unit 3 refers to the recognition rate table as shown in Table 11, and controls the display control unit 5 to display information on the current internal state of the applied data processing unit 4 and the recognition rate of each recognition target vocabulary. It is output to the unit 5, and the current recognition target vocabulary is output to the voice recognition unit 2. The display control unit 5 controls so that the display color of the button item displaying the recognition target vocabulary is distinguished by the recognition rate, and outputs the display data to the display unit. For example, a button item with a vocabulary with a recognition rate of less than 80% is red, a button item with a vocabulary of 80% or more and less than 90% is yellow, a button item with a vocabulary of 90% or more and less than 95% is light yellow, and a vocabulary of 95% or more. The button item of is controlled to be displayed in blue. In the display unit 6, for example, as shown in FIG. 13, the button item of “format” having a recognition rate of 75% is red, the “paste” having a recognition rate of 80%,
The "save" button item is displayed in yellow, the "cut" and "font" button items with a recognition rate of 93% are displayed in light yellow, and the button items of other words with a recognition rate of 95% or more are displayed in blue. With this, the user can understand the recognition performance of each vocabulary at a glance, and learn the recognition dictionary so as to improve the recognition performance of the vocabulary with poor recognition performance, or the vocabulary is not input by voice, It is understood that the user can select with the mouse, and input errors can be prevented.

Next, a ninth embodiment will be described. 14
FIG. 13 is a configuration diagram of a voice input system according to a ninth embodiment of the present invention.

The voice recognition dictionary management unit 14 is added to the configuration of the fifth embodiment. The voice recognition dictionary management unit 14 manages, for example, a plurality of voice recognition dictionaries having different characteristics such as gender and age of a speaker, and recognizes a recognition dictionary suitable for a dictionary selection request input from the voice recognition unit 2. Output to section 2.

The flow of processing of the voice input unit 1 is the same as that of the fifth embodiment, but the voice recognition unit 2 selects a dictionary used for recognition from the voice input restriction information management unit 3. Input from the voice recognition dictionary management unit 3 based on the request,
The recognition process is performed as in the fifth embodiment. Input information control unit 8
The processing flow of is similar to that of the fifth embodiment. The application data processing unit 4 has the same process flow as that of the fifth embodiment,
In the case of an input for selecting a voice recognition dictionary from the input information control unit 8, the change information of the internal state and the information of the selected voice recognition dictionary are output to the voice input restriction information management unit 3. The voice input restriction information management unit 3 outputs the current recognition target word to the voice recognition unit 2 and the display control unit 5 as in the fifth embodiment, and when there is an input regarding the selection of the voice recognition dictionary,
The ID number of the recognition dictionary is output to the voice recognition unit by referring to the recognition dictionary attribute table as shown in Table 12. For example, in FIG.
A screen for selecting a voice recognition dictionary as shown in 6 is displayed, and a case where the user selects "for men and youth" by voice input or by mouse in order to use a recognition dictionary different from the present will be described. In this case, the voice input restriction information management unit refers to the recognition dictionary attribute table as shown in Table 12 and outputs the recognition dictionary number "1" of male gender and young age (18 to 35 years old) to the voice recognition unit. Then, the fact that the dictionary with the recognition dictionary number "1" is selected is recorded in the recognition dictionary attribute table.

[0057]

[Table 12] The processing flow of the display control unit 5 and the display unit is the same as in the fifth embodiment. For example, as shown in FIG. 15, when a button item having a function of "selecting a voice recognition dictionary" is clicked or voice input on the initial screen, a screen for selecting a voice recognition dictionary as shown in FIG. 16 is displayed. The user can select a dictionary suitable for his / her gender and age and use it for recognition. Also, for example, even when the voice quality of the user is younger than the age, the user can select the dictionary created by the voice data of the speaker who is younger than the age.

As described above, since the recognition dictionary suitable for the voice quality of the user can be selected, the voice recognition error can be reduced and the user-friendly interface can be realized. Note that the attribute classification method is not limited to the example in Table 12, and may be hierarchical. For example, it may be classified into “whole”, “adult”, “adult woman” ...

Next, a tenth embodiment will be described. The configuration is similar to that of the first embodiment, but the voice input restriction information management unit 3 holds an internal state-free / restricted utterance table as shown in Table 13 instead of the internal state-continuous / isolated utterance correspondence table. is doing.

[0060]

[Table 13] The internal state-free / restricted utterance correspondence table is application data that inputs free utterances that include word order changes, abbreviations, and words (unnecessary words) that are not related to the utterance content, such as "er" and "no". The internal state of the processing unit 4 and the internal state in which it is necessary to speak so as not to make a mistake in the word order specified by the system are managed separately. The flow of processing is the same as that in the first embodiment, but the voice input restriction information management unit 3 refers to the internal state-free / restricted utterance correspondence table as shown in Table 13 and uses the above-mentioned internal state for the current internal state. Whether the input by free utterance is possible (free utterance), or whether it is necessary to utter in the word order specified by the system without making a mistake for each character (restricted utterance) is determined by the voice recognition unit 2 and the display control unit 5. Output.

In order to understand free speech, the voice recognition unit 2 detects a word based on keyword spotting for input voice, and uses syntactic constraint information for the detected time-discrete word sequence. To understand the meaning and content of utterances. On the other hand, in the case of understanding the utterance uttered so as not to make a mistake for each letter in the word order designated by the system, the recognized words and phrases are combined in accordance with the word order designated in advance by the user to compose a sentence to understand the utterance. Next, the understood utterance content is output to the application data processing unit 4 as a recognition result.

The application data processing unit 4 outputs a response such as a processing result to the display control unit 5, and outputs the change information of the internal state to the voice input restriction information management unit 3. The display control unit 5 outputs to the display unit 6 the display information from the application data processing unit 4 and the display information representing the distinction between free / restricted utterances input from the voice input restriction information management unit 3. In the display unit 6, when displaying the display information from the display control unit 5 on the screen,
Presently, when it is necessary to speak in a word order specified by the system without making a mistake for each character, the input format is visually displayed in an easy-to-understand manner.

For example, as shown in Table 14, when a seat of an aircraft is designated, preference is given to smoking / non-smoking, first / business class, window side / aisle side, etc., including word order changes, abbreviations, and unnecessary words. However, since the user can input with free utterance, no special display is provided for the input method.

[0064]

[Table 14] However, when booking a hotel in New York as shown in Table 15, "I want to stay at (hotel name) for (days)"
For example, it is displayed in an easy-to-understand manner that the desired hotel name and the length of stay must be entered in a preset word order.

[0065]

[Table 15] In this way, by visually displaying the distinction between free utterances and restricted utterances in an easy-to-understand manner, the user can understand the input utterance form at a glance and realize a user-friendly interface.

[0066]

As described above, according to the present invention, the voice input target sentence pattern, the voice input target word, the continuous / isolated utterance, the specific / unspecified speaker target, the gender and age of the recognition target speaker, the recognition performance, etc. By visually displaying the constraint information when using the voice input of, according to the state of the system,
At a glance, the user can understand the constraint conditions at the time of voice input and the utterance method. Therefore, the user can comfortably use the voice input function without being confused about the constraint information related to the use of voice input or causing an input error, and realize a human interface that is easy for a beginner to use.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of a first embodiment of a voice input system to which the present invention is applied.

FIG. 2 is a flowchart showing a processing procedure in an application data processing unit.

FIG. 3 is a diagram showing a screen example of an airline ticket reservation system.

FIG. 4 is a block diagram showing a configuration of a fourth exemplary embodiment of the present invention.

FIG. 5 is a block diagram showing a configuration of a fifth exemplary embodiment of the present invention.

FIG. 6 is a flowchart showing an operation of a voice input restriction information management unit.

FIG. 7 is an explanatory diagram showing an example of an initial screen in which a character display color is changed.

FIG. 8 is an explanatory diagram showing an example of a document edit screen.

FIG. 9 is an explanatory diagram showing an example of an initial screen in which a texture is changed.

FIG. 10 is a block diagram showing a configuration of a seventh exemplary embodiment of the present invention.

FIG. 11 is an explanatory diagram showing an example of a document edit screen.

FIG. 12 is a block diagram showing a configuration of an eighth exemplary embodiment of the present invention.

FIG. 13 is an explanatory diagram illustrating an example of a document edit screen.

FIG. 14 is a block diagram showing a configuration of a ninth exemplary embodiment of the present invention.

FIG. 15 is an explanatory diagram showing an example of an initial screen when a voice recognition dictionary is selectable.

FIG. 16 is an explanatory diagram showing an example of a screen for selecting a voice recognition dictionary.

[Explanation of symbols]

 1 voice input unit 2 voice recognition unit 3 voice input restriction information management unit 4 application data processing unit 5 display control unit 6 display unit 7 voice output unit 8 input information control unit 12 voice recognition dictionary creation unit 13 voice data management unit 14 voice recognition Dictionary management

Claims (3)

[Claims] 1. An input unit for inputting a voice, a recognition unit for recognizing an input voice from the input unit, a visual display unit for processing the recognition result and visually displaying a response, and a user's input voice. And a constraint information display means for displaying constraint information for constraining the voice input system. 2. Input means for inputting voice, recognition means for recognizing input voice from the input means, visual display means for processing the recognition result and visually displaying a response, and input voice of the user. A continuous / isolated utterance, continuous utterance count, utterance volume, individual utterance of a number / constraint information displaying means for displaying constraint information for restricting at least one of a plurality of digits. Input system. 3. Input means for inputting voice, recognition means for recognizing input voice from the input means, visual display means for processing the recognition result and visually displaying a response, voice input or other Selection information display means for displaying selection information indicating which one of the input means is selectable by using at least one of a display color, a voice input recognition rate, and a recognition rate for a user's unique utterance. A voice input system comprising: