JPH11194790A - Voice recognition actuator - Google Patents

Abstract

(57) [Summary] [PROBLEMS] To provide a speech recognition operation device that can learn to input a speech in a manner of utterance that is most easily recognized by a speech recognition unit. SOLUTION: A voice input unit 12 which inputs a voice of a speaker and outputs a voice signal, a voice recognition unit 18 which receives a voice signal and recognizes a voice of the speaker, and registers a voice pattern of a nominal name. A voice pattern registration unit 22, a learning message registration unit 48 in which a learning message is registered in advance, a voice output unit 26 for outputting a voice of a call from the other party, and a voice recognition unit 1.
A voice recognition actuating device including a display unit 30 for displaying the nominal name recognized by the control unit 8 and a dial number corresponding to the name, and a control unit 20 for controlling a predetermined processing operation based on a signal from the voice recognition unit 18 In 10, at the time of voice input of the nominal name, the voice output unit 26 outputs a learning message by voice.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice recognition operating device that recognizes voice input by a human and operates appropriately based on the voice.

[0002]

2. Description of the Related Art As a conventional voice recognition operating device, for example, a telephone subscriber's name (name) corresponding to a dialed number is directed to a microphone as described in Japanese Patent Application Laid-Open No. 61-144157. By speaking,
2. Description of the Related Art There is a voice dial device related to a telephone capable of recognizing a name by a voice recognition unit of the telephone and automatically calling a corresponding dial number.

[0003] Such a voice dial device relating to a telephone can be used for an automobile telephone or a portable telephone.
It is possible to make a call without manually operating the dial or the numeric keypad, and it is possible to make a call even if the hand is full for other work.

[0004]

However, in such a conventional voice dialing device, when the name of the dialed number is voice-inputted during registration, how to utter and input the name is the most recognized by the voice recognition unit. If the user does not know yet or is unfamiliar with it,
By inputting a voice in a manner of utterance that is difficult for the voice recognition unit to recognize, there is a possibility that the voice recognition unit may not be able to recognize the voice when calling and the dial number may not be smoothly called.

[0005] In view of the above problems, the present invention provides a speech inputting method that is most easily recognized by the speech recognizing unit even if the user is not yet proficient in speech input in the registration and speech recognition operations. It is an object of the present invention to provide a speech recognition operating device capable of learning to do.

[0006]

In order to solve the above-mentioned problems, a voice recognition operating device according to the present invention comprises a voice input section for inputting a voice of a speaker and outputting an electrical voice signal; , A voice recognition unit that recognizes the voice of the speaker by inputting, a voice pattern registration unit that registers a voice pattern of the name of the other party's telephone subscriber, a learning message registration unit in which a learning message is registered in advance, A voice output unit for outputting a call voice from the other party, a display unit for displaying the nominal name recognized by the voice recognition unit and / or a dial number corresponding thereto, and a signal from the voice recognition unit. A control unit for controlling registration, recognition, reading, display, and other predetermined processing operations, wherein when the nominal name is input by voice, the learning message is sent from the voice output unit. It is obtained by a configuration in which di is the audio output.

[0007] According to the voice recognition operating device having such a configuration, the learning message registered in the learning message registration unit is output from the voice output unit by voice when the nominal name is input, so that the user can speak in advance. Therefore, even if the user has not yet mastered the voice input in the registration and voice recognition operations, the user can input the voice in the most recognizable way for the voice recognition unit. It becomes possible.

[0008]

Embodiments of the present invention will be specifically described below with reference to the drawings. 1 and 2
FIG. 1 is a diagram referred to for describing a portable telephone 10 according to a first embodiment of a voice recognition operating device according to the present invention.

In the portable telephone 10 shown in FIG.
Voice input unit 1 to which voice is input when talking with the other party
2 (microphone) transmits a voice signal to the communication circuit 34, and further the voice signal is transmitted from the communication circuit 34 to the high frequency unit 24.
Is transmitted to the nearest base station from the antenna 24a toward the other party.

When a response from the other party is received by the antenna 24a from the base station by radio, the received signal is
4 is sent to the voice output unit 26 (speaker) via the communication circuit 34, and the voice of the response is heard from the voice output unit 26 to the speaker (user) wearing the ear.

When calling the other party, the operation unit 36
A call can be made by pressing the dial number with the key of, but when the other party's nominal name is registered in the nominal name pattern storage unit (voice pattern registration unit) 22, the user inputs the nominal name by voice. By speaking toward the unit 12, a call can be automatically made to the other party by the dial circuit included in the communication circuit 34.

In this case, the audio signal from the audio input unit 12 is amplified by the amplifier unit 14, converted from an analog signal to a digital signal by the A / D unit 16 (analog / digital converter), and the digital signal is input. The recognized voice recognition unit 18 recognizes the input voice and checks and selects the same voice pattern from the nominal names registered in the nominal name pattern storage unit 22.

When the voice recognition unit 18 outputs a signal related to the nominal name to the control unit 20, the control unit 20 selects one of the dial numbers registered in the dial number storage unit 38 in advance so as to correspond to the nominal name. By calling the associated dial number and sending it to the dial circuit of the call circuit 34, a call is automatically made.

The portable telephone 10 has a recording / reproducing section 40 composed of an IC memory or the like, and can record a voice during a call or in an answering machine mode, and reproduce it later. The portable telephone 10 has a temperature measurement sensor 42. The temperature measurement sensor 42 measures the temperature of the environment and notifies the control unit 20 of the temperature. Can be controlled so as not to deteriorate.

In the portable telephone 10, the timer 44 always outputs a clock signal to the control unit 20 so that the date and time can be displayed on the display unit 30 so that the date and time displayed on the display unit 30 can be changed. It is going to progress.

In the present embodiment, in addition to the configuration shown in FIG. 1, a practice voice synthesizer 48 as shown in FIG.
(Learning message registration unit) is provided. The practice voice synthesis unit 48 causes the model output model voice synthesized with the voice to be output from the voice output unit 26 before the practice voice is input to the voice input unit 12.

The practice voice synthesizer 48 includes a voice output unit 2
6 to output the model voice, but compared to unnatural voice without inflection and accent like IC memory,
The voice output unit 26 has a function of outputting a more natural voice that takes into account both intonation and accent.

Next, a procedure for registering a name and its dial number will be described with reference to the flowchart of FIG. When the registration mode is selected by operating the keys of the operation unit 36, an initial registration screen is first displayed on the display unit 30 (step S1), and then, for example, "Please input a name with a key" is displayed. Is performed (step S2). When the user sees the display and inputs, for example, "Yamada" with the key of the operation unit 36, "Yamada" is displayed on the display unit 30 (step S3), and the nominal name is stored in the dial number storage unit 38. Registered in.

Next, "Enter the dial number with the key" is displayed on the display unit 30 (step S4). When the user inputs the dial number, "Yamada 03-OOOO- ○" is displayed on the display unit 30. Is displayed (step S5), and the dialed number is registered in the dialed number storage unit 38.

Next, a display such as "Please practice like an output voice in practice" is displayed on the display unit 30 (step S6). The natural and clear pronunciation of “Yamada” stored in the unit 48 is output from the sound output unit 26 and is heard. The user mimics the pronunciation and says "Yamada" in practice.

Then, "Please pronounce the nominal name on the microphone" is displayed on the display unit 30 (step S7). Here, "Yamada" is newly registered as the nominal name in which the voice pattern is registered in the nominal name pattern storage unit 22 for the first time. "Speak into the microphone in the way you practiced earlier.

Then, a voice signal is input from the voice input unit 12 to the voice recognition unit 18 via the amplifier unit 14 and the A / D unit 16, and “Yamada” is stored in the nominal name pattern storage unit 22 by the signal from the voice recognition unit 18. Is officially registered. Then, a message "Registration of the nominal name has been completed" is displayed on the display unit 30, and a series of operations for registration are completed (step S8).

FIGS. 4 and 5 are views referred to for describing a second embodiment of the present invention. In the second embodiment, as shown in FIG. 4, the nominal name pattern storage unit 22 is provided with an unspecified pattern storage unit in addition to the nominal name pattern storage unit. For example, a voice pattern of "Keisatsu" of "police" is registered in the section.

In the dial number storage section 38, a dial number "110" corresponding to the "key" is registered. Further, the recording / reproducing unit 40 is provided with a registration voice storage unit and a practice voice storage unit.

Next, the operation procedure of the speech recognition will be described with reference to FIG.
A description will be given based on the flowchart of FIG. When the recognition mode is selected by operating the operation unit 36, an initial display screen of the practice mode first appears on the display unit 30 (step S1). A user who is already proficient in voice input in the voice recognition operation does not need to practice in particular. By pressing the pass button (key), the user skips the practice mode and immediately shifts to the recognition mode. You can make a call.

A user who has not yet mastered the voice input in the voice recognition operation can execute the practice mode. When the display of the practice mode appears on the display unit 30, a display such as "Let's practice the pronunciation of voice input" appears on the display unit 30 (step S2).
Next, for example, a message “Let's call“ Keisatsu ”(famous learning name)” is displayed on the display unit 30 (step S3).

Next, a message "Please practice like an output voice" is displayed on the display unit 30 (step S).
4) Subsequently, the voice stored in the practice voice storage unit of the recording / reproducing unit 40 is output as "Keisatsu" from the voice output unit 26 and is heard by the user.

After that, the display unit 30 displays a screen for waiting for the voice to say "Please say this" (step S5), and the user who has seen it hears the voice input unit 12 earlier. I simulate the pronunciation of "Keisatsu."

As a result, a voice signal is output from the voice input unit 12 and sent to the voice recognition unit 18 via the amplifier unit 14 and the A / D unit 16. By collating with the voice pattern in the pattern storage unit, the voice pattern of “Katsu” is recognized, and a signal related to the “Katsu” is output to the control unit 20. The control unit 20 calls the dial number 110 related to “Keisatsu” from the dial number storage unit 38 based on this signal,
The information of the dial number 110 is output to the display unit 30.

For this reason, the display unit 30 displays "Keisetsu 110
Is displayed (step S6), it is understood that the user's utterance has been appropriately recognized by the voice recognition unit 18, and the practice mode ends (step S7).
In this way, the user can learn how to make a speech and then input a voice, thereby making it possible to use the voice recognition function of the mobile phone 10.

FIG. 6 is a flowchart for explaining the third embodiment of the present invention. In the third embodiment, when a nominal name is registered, the tempo is to be derived. That is, when the registration mode is selected by operating the operation unit 36, an initial screen of the registration mode is first displayed on the display unit 30 (step S1).

Next, the display section 30 displays "Please input the name to be registered" (step S2). When the user inputs the name in katakana using the keys of the operation section 36, the display is continued. The unit 30 displays "Please sound according to the tempo of the output sound" (step S3).

Immediately thereafter, information from the registration voice storage unit of the recording / playback unit 40 is output as voice from the voice output unit 26.
For example, a sound such as “beep, beep,...” Is output. For this reason, a user who has not yet mastered the voice input at the time of registration of the nominal name inputs the nominal name to the voice input unit 12 well according to the tempo of the voice “pip, pip, pip, ...”. And the nominal name can be safely registered in the nominal name pattern storage unit 22 (step S4).

FIG. 7 is a flowchart for explaining a fourth embodiment of the present invention. The fourth embodiment also seeks to derive a tempo when registering a nominal name, but unlike the third embodiment in which a tempo is induced by voice, the display unit 30 The displayed tempo of the sound is guided by the blinking of the displayed dot (circle).

That is, the initial screen of the registration mode is displayed on the display unit 3.
0 (step S1), and after inputting the name to be registered in katakana using the keys while looking at the next display (step S2), a dot graphic D is displayed on the display unit 30 and " Please sound according to the flashing tempo of the dot "(step S3). The user can well pronounce the nominal name in accordance with the blinking tempo of the dot on the display unit 30 and input the nominal name to the voice input unit 12, and register the nominal name in the nominal name pattern storage unit 22 safely. (Step S4).

FIG. 8 is a flowchart for explaining the fifth embodiment of the present invention. The fifth embodiment also seeks to derive the tempo when registering a nominal name. However, unlike the fifth embodiment, which is performed by flashing a sound or a dot as in the above-described embodiment, the display unit 30 has a band shape. By sequentially changing the color of a character surrounded by a plurality of square frames S arranged in a row from the end, the tempo of sound generation is induced in accordance with the speed of the color change.

That is, the initial screen of the registration mode is displayed on the display unit 3.
0 is displayed (Step S1), and the next display (Step S2) is entered by inputting the nominal name to be registered with the key.
The display unit 30 displays the characters surrounded by the rectangular frame S of the number of the characters with the nominal name, which are continuously arranged in a band shape, and “according to the speed of the color change of the characters in the lower rectangular frame. "Please pronounce" is displayed (step S3).
The user can skillfully pronounce the nominal name and input it to the voice input unit 12 in accordance with the discoloration tempo of the plurality of characters on the display unit 30, and the nominal name can be safely stored in the nominal name pattern storage unit 22. Can be registered (Step S
4).

Although the embodiments of the present invention have been specifically described above, the present invention is not limited to the above-described embodiments, and may be variously modified based on the technical idea of the present invention. Can be changed.

[0039]

As described above, according to the voice recognition operating device of the present invention, even if the user has not yet mastered the voice input in the registration and voice recognition operations,
Since the voice recognition unit can learn to input a voice in a manner of utterance that is most easily recognized, it is possible to smoothly perform voice input for registration of a nominal name and voice recognition at the time of calling.

[Brief description of the drawings]

FIG. 1 is a block circuit diagram showing a configuration of a portable telephone 10 according to a first embodiment of a voice recognition operation device according to the present invention.

FIG. 2 is a block circuit diagram showing a main part of the portable telephone 10 in FIG.

FIG. 3 is a flowchart illustrating a flow of a change in display content of a display unit 30 during an operation according to the first exemplary embodiment.

FIG. 4 is a block circuit diagram showing a main part of a portable telephone according to a second embodiment of the present invention.

FIG. 5 is a flowchart illustrating a flow of a change in display content of a display unit during operation according to the second embodiment;

FIG. 6 shows a display unit 3 during operation according to the third embodiment of the present invention.
11 is a flowchart showing a flow of change of display contents of 0.

FIG. 7 shows a display unit 3 during operation according to the fourth embodiment of the present invention.
11 is a flowchart showing a flow of change of display contents of 0.

FIG. 8 shows a display unit 3 during operation according to the fifth embodiment of the present invention.
11 is a flowchart showing a flow of change of display contents of 0.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 10 Mobile telephone 12 Audio input part 14 Amplifier part 16 A / D part 18 Speech recognition device 20 Control part 22 Nominal name pattern storage part 23 Noise removal part 24 High frequency part 24a Antenna 26 Audio output part 30 Display part 34 Communication circuit 36 Operation Unit 38 dial number storage unit 40 recording and playback unit 42 temperature measurement sensor 44 timer 48 practice voice synthesis unit

Claims (5)

[Claims] A voice input unit for inputting a voice of a speaker and outputting an electrical voice signal; a voice recognition unit for inputting the voice signal and recognizing the voice of the speaker; A voice pattern registration unit for registering the voice pattern of the name of the person, a learning message registration unit in which a learning message has been registered in advance, a voice output unit for outputting a call voice from the other party, and the voice recognition unit. A display unit that displays the nominal name and / or a dial number corresponding thereto, and a control unit that controls registration, recognition, reading, display, and other predetermined processing operations based on a signal from the voice recognition unit. The voice recognition operation device according to claim 1, wherein the voice output unit outputs the learning message when the name is input by voice. 2. A voice input unit for inputting a voice of a speaker and outputting an electrical voice signal; a voice recognition unit for inputting the voice signal and recognizing the voice of the speaker; A voice pattern registration unit for registering a voice pattern of a nominal name of a person, a recording / reproducing unit in which a prominent learning nominal name is registered in advance, a voice output unit for outputting a call voice from the other party, and the voice recognition unit. A display unit for displaying the recognized nominal name and / or a dial number corresponding thereto, and a control for controlling registration, recognition, reading, display, and other predetermined processing operations based on a signal from the voice recognition unit. And a voice recognition actuating device comprising: a voice input of the famous learning nominal name at the time of voice input of the nominal name, and a prominent dial number corresponding to the nominal name is displayed on the display unit for learning. Speech recognition actuation device, characterized in that it is. 3. The voice output unit outputs the pre-registered famous learning nominal name as a model before inputting the famous learning nominal name at the time of registration of the nominal voice pattern. The voice recognition operating device according to claim 2, wherein 4. A voice input unit for inputting a voice of a speaker and outputting an electrical voice signal; a voice recognition unit for receiving the voice signal and recognizing the voice of the speaker; A voice pattern registration unit for registering a voice pattern of a nominal name of a person, a voice output unit for outputting a call voice from the other party, and displaying the nominal name recognized by the voice recognition unit and a dial number corresponding thereto. A display unit, and a control unit that controls registration, recognition, reading, display, and other predetermined processing operations based on a signal from the voice recognition unit. A voice recognition operating device, wherein a display for guidance for adjusting the tempo of utterance at the time of voice input is displayed on the display unit. 5. A voice input unit for inputting a voice of a speaker and outputting an electrical voice signal; a voice recognition unit for inputting the voice signal and recognizing the voice of the speaker; A voice pattern registration unit for registering a voice pattern of a nominal name of a person, a voice output unit for outputting a call voice from the other party, and displaying the nominal name recognized by the voice recognition unit and a dial number corresponding thereto. A display unit, and a control unit that controls registration, recognition, reading, display, and other predetermined processing operations based on a signal from the voice recognition unit. A voice recognition operating device, wherein at the time, a voice for guidance for adjusting the tempo of utterance at the time of voice input is output from the voice output unit.