JPH11234382A - Voice recognition device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a voice recognition device having a high recognition rate which selects a voice reference pattern already registered when is determines that the registered voice reference pattern is more appropriate than a newly registered voice reference pattern. SOLUTION: In this voice recognition device which is provided with a voice inputting part 12, a voice recognizing part 18, a voice pattern registering part and a controlling part 20 which controls registration, recognition, read, display and other prescribed processing operations based on a signal from the part 18, the voice pattern registering part can register plural kinds of different voice reference patterns of one input voice and the part 20 can optionally select and set a desired voice reference pattern from the pattern registering part.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice recognition operation device which recognizes voice input by a specific speaker and appropriately operates 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 as described in Japanese Patent Application Laid-Open No. 61-144157 is spoken toward a microphone. As a result, 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 a car phone or a mobile phone, and it is possible to make a call without manually operating a dial or a numeric keypad. You can make a call even if you are

[0004]

However, in the conventional voice dialing device as described in the above publication, when registering a nominal name corresponding to a dialed number,
The characteristics of the circuit elements of the device, the quality of the voice, the way of uttering, etc. may change due to changes in the environmental temperature at the time of registration and at the time of calling. Voice quality, vocalization, etc. may change.

[0005] When the characteristics of the circuit elements of the apparatus, the quality of the voice, the manner of utterance, etc. are changed due to the change of the temperature or the time of the environment, the input voice pattern is the voice pattern registered before the change. In some cases, spectrum information and the like may be different from each other, and it may be difficult for the voice recognition unit to accurately recognize voice, and a dial number may not be called smoothly. In the above prior art, no consideration is given to the failure of the reference pattern of the voice to be recognized.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and when it is determined that a registered voice reference pattern is more appropriate than a newly registered voice reference pattern, the newly registered voice reference pattern is used. It is an object of the present invention to provide a speech recognition operation device with a high recognition rate, which can cancel the registration of a registered speech reference pattern and select the registration.

[0007]

In order to solve the above-mentioned problems, a voice recognition operating device according to the present invention comprises: a voice input unit for inputting a voice of a speaker and outputting an electrical voice signal; A voice recognition unit for inputting a signal to recognize the voice of the speaker, a voice pattern registration unit for registering a voice pattern of the other party's name, and a registration / recognition / reading / reading unit based on a signal from the voice recognition unit. In a voice recognition operation device having a control unit that controls display and other predetermined processing operations, a plurality of different types of voice reference patterns can be registered for one input voice in the voice pattern registration unit, The control unit can arbitrarily select and set a desired audio reference pattern from the audio pattern registration unit. Also, the control unit is configured to compare the newly registered voice reference pattern of the input voice with the already registered voice reference pattern, and select and set again the one with the higher recognition rate. Furthermore, after performing a recognition operation on the newly input voice by the voice recognition unit, a voice reference pattern determined to have a high recognition rate can be arbitrarily selected from the voice reference patterns registered in the voice pattern registration unit. .

According to the voice recognition operating device having such a configuration, a plurality of types of voice reference patterns registered under different conditions are registered in the voice pattern registration unit, and can be arbitrarily re-registered. Therefore, it can always be used as a device having a high recognition rate that is optimal for the user.

[0009]

Embodiments of the present invention will be specifically described below with reference to the drawings.

FIG. 1 and FIG. 2 are views referred to for explaining a portable telephone 10 according to an embodiment of a voice recognition operating device according to the present invention. FIG. 1 is a block circuit diagram showing a configuration of a mobile phone according to an embodiment of a voice recognition operation device according to the present invention. FIG. 2 is a chart showing a registration state of the voice pattern registered in the nominal name pattern storage unit 22 of the mobile phone in FIG.

In the portable telephone 10 shown in FIG. 1, when talking with the other party, a voice input unit 12 to which voice is input is provided.
A voice signal is transmitted from the (microphone) to the communication circuit 34, and further the voice signal is transmitted from the communication circuit 34 to the high-frequency unit 24, and the radio is transmitted from the antenna 24a to the nearest base station 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 call circuit 34, and then sent from the call circuit 34 to the audio output unit 26 (speaker), from which the speaker who puts his / her ear can hear the response voice. It has become.

When calling the other party, the operation unit 3
It is possible to make a call by pressing the dial number with the key No. 6, but when the other party's nominal name is registered in the nominal name pattern storage unit (voice pattern registration unit) 22, the user By speaking toward the input unit 12, it is possible to automatically call the other party by the dial circuit included in the communication circuit 34.

In this case, the audio signal from the audio input section 12 is amplified by the amplifier section 14 and the A / D conversion section 16
(Analog / digital conversion device) converts the analog signal into a digital signal, and the voice recognition unit 18 that has input the digital signal recognizes the input voice, and the nominal name registered in the nominal name pattern storage unit 22. Match and select the same from

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 so as to correspond to the nominal name in advance. By calling the associated dial number and sending it to the dial circuit of the call circuit 34, the call is automatically originated.

The mobile phone 10 has a recording / reproducing section 40 composed of an IC memory or the like, and can record voice from the other party when the telephone is in the answering machine mode, and can reproduce the voice later. The mobile phone 10 also has a temperature measurement sensor 42. The temperature measurement sensor 42 measures the temperature of the environment and informs the control unit 20 so that the control unit 20 can control the brightness of the LCD constituting the display unit 30. It can be controlled so as not to deteriorate.

The mobile phone 10 has a timer 4
4 (time measuring unit) is provided, which constantly outputs a clock signal to the control unit 20 to advance the date and time displayed on the display unit 30.

In the present embodiment, as shown in FIG. 2, the nominal name pattern storage section 22 stores the voice pattern of the nominal name of the telephone subscriber corresponding to the dial number registered in the dial number storage section 38. Are registered, and three or more sets of different patterns are registered as voice patterns of the nominal name, and each pattern has a priority, and is used at the time of recognition according to the priority.

In such a portable telephone 10, when making a call, the control unit 20 controls the nominal name pattern storage unit so that the most appropriate type of voice pattern for the voice recognition unit 18 is recognized by sequentially comparing it with the input voice. 22 is controlled. For this reason, the voice recognition unit 1 uses the voice reference patterns registered under different conditions according to changes in environment, temperature, and the like.
8 can recognize the correct name by the optimum voice reference pattern by voice, and can smoothly dial the dialed number. However, since the optimal voice reference pattern is not always collated first, it may take time or may not be recognized. At this time, the recognition rate can be improved by changing the order so that the recognizable voice reference pattern is selected first or deleting unnecessary voice reference patterns.

As a result, the control unit 20 controls the nominal name pattern storage unit 22 so that the voice recognition unit 18 matches the input voice with a voice reference pattern that is optimal for the voice recognition unit 18 when making a call.

In the above-described embodiment, the case where the present invention is applied to the mobile phone 10 has been described. However, the present invention is not limited to the mobile phone 10 and is not limited to the mobile phone 10 or another telephone such as a car phone or a facsimile. And any other devices and devices such as personal computers.

Although the embodiments of the present invention have been specifically described above, the present invention is not limited to the above-described embodiments, and various other modifications are possible based on the technical idea of the present invention. Can be changed.

[0023]

As described above, according to the voice recognition operating device of the present invention, a plurality of voice reference patterns are registered,
When the user determines that the old voice reference pattern is easier to recognize, the voice recognition is performed using the old voice reference pattern, so that the recognition rate at the time of recognition can be improved.

[Brief description of the drawings]

FIG. 1 is a block circuit diagram showing a configuration of a mobile phone according to an embodiment of a voice recognition operation device according to the present invention.

FIG. 2 is a table showing a registration state of voice patterns registered in a nominal name pattern storage unit 22 of the mobile phone in FIG. 1;

[Explanation of symbols]

 Reference Signs List 10 mobile phone 12 voice input unit 14 amplifier unit 16 A / D conversion unit 18 voice recognition unit 20 control unit 22 nominal name pattern storage unit 23 noise removal unit 24 high frequency unit 24a antenna 26 voice output unit 30 display unit 32 recording / playback unit 34 Communication circuit 36 Operation section 38 Dial number storage section 40 Recording / playback section 42 Temperature measurement sensor 44 Timer

Claims (3)

[Claims] A voice input unit for inputting a voice of a speaker and outputting an electrical voice signal; a voice recognizing unit for receiving the voice signal and recognizing the voice of the speaker; A voice pattern registration unit for registering a voice pattern, and a control unit for controlling registration, recognition, reading, display, and other predetermined processing operations based on a signal from the voice recognition unit. The voice pattern registration unit can register a plurality of different types of voice reference patterns for one input voice, and the control unit can arbitrarily select and set a desired voice reference pattern from the voice pattern registration unit. A speech recognition operating device characterized by the following. 2. The apparatus according to claim 1, wherein the control unit compares the voice reference pattern of the newly registered input voice with a voice reference pattern already registered, and selects and re-sets a voice recognition pattern having a higher recognition rate. The voice recognition operating device according to claim 1, wherein: 3. After performing a recognition operation on a newly input voice by the voice recognition unit, a voice reference pattern determined to have a high recognition rate can be arbitrarily selected from the voice reference patterns registered in the voice pattern registration unit. The voice recognition operating device according to claim 1, wherein the voice recognition device is configured as follows.