JP2005110180A - Radio communication terminal - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a radio communication terminal with a voice recognition function which can automatically operate the voice recognition function when it is necessary without an operation of a voice recognition-specific key and which can suppress utterance of persons except a user and a response to a surrounding noise minimum. <P>SOLUTION: In the presence of change in external light, voice recognition processing is started. When a word inputted thereafter, namely a word spoken by a user coincides with a word having already registered, a response is performed by a vibration of a vibrator 111, lighting of an LED portion 112, or an output of a musical tone from a speaker 113. Thus, even if a dedicated key for start of voice recognition is not operated, the voice recognition processing is started by the change of the external light. Therefore, even if a radio communication terminal 100 is put in e.g. a bag, a response is performed by speaking in the presence of the change in the external light, thereby enabling the radio communication terminal 100 to be easily found. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a wireless communication terminal such as a mobile phone, a PHS (Personal Handy-phone System), a PDA (Personal Digital Assistant), and more particularly to a wireless communication terminal having a voice recognition function.

  2. Description of the Related Art Conventionally, the above-described wireless communication terminals have been proposed that have a voice recognition function and that can realize part of the functions of the wireless communication terminal by voice using this voice recognition function (for example, patents). Reference 1).

  FIG. 3 is a block diagram showing a schematic configuration of a mobile phone having a voice recognition function disclosed in Patent Document 1. In FIG.

  The mobile phone shown in FIG. 3 includes a radio unit 31 that transmits and receives radio signals, an operation unit 32 that performs various operations on the mobile phone, a display unit 33 that displays a character string, a recognition word that is fixed for voice recognition, A data ROM (Read Only Memory) 34 for storing data such as response voice, a control unit 35 comprising a main CPU (Central Processing Unit) and DSP (Digital Signal Processor) for controlling each part of the cellular phone, and voice recognition processing A voice recognition unit 36 that performs A / D, an A / D (Analog-to-Digital) converter 37, a switch 38 that switches a connection destination of the A / D converter 37, a microphone 39 to which voice is input, and a speaker that outputs voice. 40. The operation unit 32 includes a registration key for registering a name and telephone number in a memory, a voice recognition dedicated key, and the like. The voice recognition unit 36 does not operate during normal operation, and performs voice recognition processing only when a voice recognition dedicated key (not shown) of the operation unit 32 is pressed and the state is detected by the control unit 35.

  Next, the operation of the mobile phone having the above configuration will be described. When the user presses a voice recognition dedicated key (not shown) of the operation unit 32, the control unit 35 detects the state and activates the voice recognition unit 36 to start the voice recognition process. After the user presses the voice recognition dedicated key and speaks into the microphone 39, the voice signal from the microphone 39 is input to the A / D converter 37 and converted into a digital signal. The digitally converted audio signal (audio data) is input to the audio recognition unit 36. At this time, the switch 38 is switched to the voice recognition unit 36 side.

  The voice recognition unit 36 performs voice recognition processing on the input voice data, and inputs the result to the control unit 35 when the recognition result is confirmed. The control unit 35 displays data corresponding to the recognition result input from the voice recognition unit 36 on the display unit 33, and outputs a response voice corresponding to the recognition result from the speaker 40. At this time, as the recognition word data, the fixed value of the function name of the mobile phone is stored in advance in the data ROM 34 and is used. As for the name of the memory dial, a plurality of single-tone data are stored in advance in the data ROM 34, and are used by connecting them.

Japanese Patent Application Laid-Open No. 11-112633 (page 3, page 4, FIG. 2, FIG. 3)

  However, a conventional mobile phone having a voice recognition function has the following problems. In other words, although there is a voice recognition function, the function can be performed only by operating the voice recognition dedicated key. Therefore, if the voice recognition dedicated key is not operated, no response can be obtained even if calling to the mobile phone. . For this reason, it takes a long time to search when the mobile phone is kept in a bag, for example.

  The recognition word used for speech recognition is fixed data stored in the data ROM 34 before the mobile phone is delivered to the user (for example, at the time of factory shipment). Will respond.

  The present invention has been made in view of the above points, and can automatically activate a speech recognition function when necessary without operating a dedicated voice recognition key. Another object of the present invention is to provide a wireless communication terminal capable of minimizing the response to ambient noise.

  In order to solve the above-described problems, a wireless communication terminal according to the present invention includes a registration unit that registers a keyed word and a response operation, a voice input unit that inputs voice, and a voice input by the voice input unit. A voice recognition means for recognizing a word; a light detection means for detecting light outside the apparatus; and an instruction for starting a voice recognition process to the voice recognition means when there is a change in the output of the light detection means. A response start instruction output unit; a collation unit that collates a word registered in the registration unit with a word that has been registered and is recognized by voice input after the voice recognition process is started; and the collation When the word registered in the registration unit matches the word recognized by voice input after the voice recognition process starts from the collation result by the unit, vibration, light And a, a response means for generating at least one of the fine tone.

  According to this configuration, when the external light changes, the speech recognition process is started, and when the speech (user call) word input thereafter matches the registered word, vibration, light or Generate and respond to musical sounds. Therefore, since the voice recognition process is started by the change of the external light without operating the dedicated key for starting the voice recognition, it responds by calling if there is a change in the light even when the wireless communication terminal is put in the bag. Therefore, it is possible to easily find a wireless communication terminal.

  The wireless communication terminal of the present invention includes a voice input means for inputting voice, a voice recognition means for recognizing a word inputted by the voice input means, a word recognized by the voice recognition means, and a response. A registration unit for registering an operation; a light detection unit for detecting light outside the apparatus; and a response for giving an instruction to start the voice recognition process to the voice recognition unit when there is a change in the output of the light detection unit A start instruction output unit, a collation unit that collates a word registered in the registration unit and a word that has been registered and is recognized by voice input after the start of the speech recognition process; and the collation unit If the word registered in the registration means matches the word recognized by speech input after the start of the speech recognition process, the vibration, light, and light according to the response operation registered in the registration means And a, a response means for generating at least one of sound.

  According to this configuration, the same operation and effect as the above-described wireless communication terminal of the present invention can be obtained, and the word to be registered can be input by voice, so that the word can be easily registered.

  The wireless communication terminal according to the present invention includes a voice input unit for inputting voice, a voice recognition unit for recognizing a word input by the voice input unit, and a feature of the voice input by the voice input unit. A voice feature quantity detecting means for detecting a quantity; a registration means for registering the word and response action recognized by the voice recognition means in association with the voice feature quantity detected by the voice feature quantity detection means; A light detection means for detecting light outside the apparatus, a response start instruction output means for giving an instruction to start the voice recognition processing to the voice recognition means when there is a change in the output of the light detection means, and the registration The word registered in the means is compared with the word recognized after voice registration after the word is registered and after the voice recognition processing is started, and the feature amount of the voice inputted after the voice recognition processing is started A collating unit that collates whether the feature value of the voice registered in the registering unit is within a determination criterion, and a speech word that is input after the start of the speech recognition process matches a registered word from the collation result by the collating unit. And response means for generating at least one of vibration, light, and musical sound according to the response operation registered in the registration means only when the feature amount of the sound is within the determination criterion.

  According to this configuration, the same operation and effect as the wireless communication terminal of the present invention described above can be obtained, and the feature amount of the user's voice is recorded at the time of word registration by voice, and this feature amount is used as a criterion for speech recognition. Therefore, it is possible to minimize the utterance of people other than the user and the response to ambient noise. That is, it is possible to obtain a speech recognition function with a lower error rate than in the case of collating only with words.

  In the wireless communication terminal of the present invention, in any of the wireless communication terminals described above, the response means generates vibration by driving a vibrator.

  According to this configuration, since the response to the user's call is performed by operating the vibrator originally provided in the wireless communication terminal, it is not necessary to provide a dedicated vibrator, thereby minimizing the cost increase. And space saving.

  In the wireless communication terminal of the present invention, in any of the wireless communication terminals described above, the response means generates light by driving a light emitting element.

  According to this configuration, since the response to the user's call is performed by turning on the light emitting element for incoming call notification originally provided in the wireless communication terminal, there is no need to provide a dedicated light emitting element, which increases the cost. As well as space saving.

  In the wireless communication terminal of the present invention, in any of the wireless communication terminals described above, the response means generates a musical sound by driving a speaker.

  According to this configuration, since the response to the user's call is performed by operating the speaker originally provided in the wireless communication terminal, it is not necessary to provide a dedicated speaker, so that the cost increase can be minimized. And space saving.

  According to the present invention, the voice recognition process is started when there is a change in the external light without performing the operation of the voice recognition dedicated key, and the words of the voice (user call) inputted after that are already registered. When the word matches, it responds by generating vibration, light, or musical sound, so that the wireless communication terminal can be easily found even if it is placed in a bag, for example.

  In addition, according to the present invention, the feature amount of the user's voice is recorded at the time of word registration by voice, and this feature amount is used as a criterion for speech recognition. Can be minimized.

  Hereinafter, the best mode for carrying out the present invention will be described in detail with reference to the drawings.

(Embodiment 1)
FIG. 1 is a block diagram showing a schematic configuration of a radio communication terminal according to Embodiment 1 of the present invention.

  In FIG. 1, a wireless communication terminal 100 according to the present embodiment includes a light detection unit 101 that detects light, a control unit 102 that controls each unit of the device, a timer 103 that measures time from the start of speech recognition, A recording unit 104 for recording a word for recording, a microphone 105 for inputting voice, an operation unit 106 including a key input means, a voice recognition unit 107 for recognizing a word from voice, and registration of an input voice word A collation unit 108 that collates with a completed word, and a response processing unit 109 that performs a response process in response to a call from the user based on the collation result of the collation unit 108 are provided. The response processing unit 109 includes a vibrator driving unit 109a that drives a vibrator 111 that notifies an incoming call by generating mechanical vibration, and an LED driving unit that drives an LED (light emitting diode) unit 112 that notifies the incoming call by emitting light. 109b and a speaker driving unit 109c that drives the speaker 113 that notifies an incoming call by outputting a musical sound. The vibrator 111, the LED unit 112, and the speaker 113 are originally provided in the wireless communication terminal.

  The recording unit 104 corresponds to a registration unit. The microphone 105 corresponds to a voice input unit, the voice recognition unit 107 corresponds to a voice recognition unit, and the light detection unit 101 corresponds to a light detection unit. The control unit 102 corresponds to a response start instruction output unit, and the verification unit 108 corresponds to a verification unit. The response processing unit 109 corresponds to response means.

  Next, the speech recognition process of the wireless communication terminal 100 having the above configuration will be described. First, the user uses the operation unit 106 to key-in a word and a response operation (response by vibration, response by light, or response by tone) that the wireless communication terminal 100 responds to the call of the user. The input word and response action are recorded in the recording unit 104. After the response word and the response action are recorded, the wireless communication terminal 100 is assumed to be placed in a place where outside light is blocked, for example, in a cage. The light detection unit 101 detects the intensity of external light from the time when the power is supplied to the wireless communication terminal 100 and inputs the result to the control unit 102. When the output value of the detection unit 101 changes and the control unit 102 detects a change in the output value of the light detection unit 101, the control unit 102 instructs the voice recognition unit 107 to start the voice recognition process. At this time, if the response processing unit 109 does not respond during the time set by the timer 103, the voice recognition process is stopped.

  After the voice recognition unit 107 starts the voice recognition process, when voice is input from the outside to the microphone 105, that is, when the user makes a utterance, the voice recognition unit 107 performs voice recognition on the utterance and detects a word. . Then, the detected word is input to the matching unit 108. When a word is input from the speech recognition unit 107, the matching unit 108 reads the word registered in the recording unit 104 and compares it, and if not matched, inputs a mismatch result to the control unit 102, and matches. In this case, an ON signal is input to the response processing unit 109. When an ON signal is input from the collating unit 108, the response processing unit 109 receives at least one of the vibrator driving unit 109a, the LED driving unit 109b, and the speaker driving unit 109c based on the response operation registered in the recording unit 104. Is operated to vibrate the vibrator 111, turn on the LED unit 112, or reproduce the musical sound from the speaker 113 to notify the user of the location of the wireless communication terminal 100.

  As described above, according to the wireless communication terminal 100 of the present embodiment, the speech recognition process is started when there is a change in the external light, and the input speech (user call) word is registered. If it matches the word, it responds by generating vibration, light or music. Therefore, since the voice recognition process is started by the change of the external light without operating the dedicated key for starting voice recognition, it is easily searched for by responding by calling even when the wireless communication terminal 100 is put in the bag. be able to.

  In the above embodiment, the word to be registered and the response operation are key-inputted by the operation unit 106, but may be registered by voice input from the microphone 105. At this time, the input voice is recognized by the voice recognition unit 107, and the result is registered in the recording unit 104.

(Embodiment 2)
FIG. 2 is a block diagram showing a schematic configuration of the radio communication terminal according to the second embodiment of the present invention. In FIG. 2, the same reference numerals are given to the parts having the same functions as those of the wireless communication terminal of the first embodiment described above, and the description thereof is omitted.

  As illustrated in FIG. 2, the wireless communication terminal 200 according to the present embodiment includes a measurement unit 201 that detects a feature amount of speech input by a microphone 105, a word recognized by the speech recognition unit 107, and a response operation. And a recording unit 202 for registering the input voice feature value detected by the measuring unit 201, a word registered in the recording unit 202, and after the word is registered, the control unit 102 to the speech recognition unit 107. Are compared with words recognized by voice input from the microphone 105 after the voice recognition process start instruction is output, and the feature amount of the voice input from the microphone 105 after the voice recognition process start instruction is output is recorded. And a collation unit 203 for collating whether or not the voice feature value registered in the unit 202 is within the determination criterion.

  The measurement unit 201 corresponds to a voice feature amount detection unit, and the recording unit 202 corresponds to a registration unit.

  From the collation result of the collation unit 203, the response processing unit 109 matches the word of the voice input from the microphone 105 after the output of the voice recognition process start instruction, and the feature amount of the voice is within the criterion. Only in this case, at least one of the vibrator drive unit 109a, the LED drive unit 109b, and the speaker drive unit 109c is operated according to the response operation registered in the recording unit 202, and vibration of the vibrator 111, lighting of the LED unit 112, or speaker The musical sound from 113 is reproduced to notify the user of the location of the wireless communication terminal 200.

  Next, the voice recognition process of the radio communication terminal 200 having the above configuration will be described. First, a user inputs a word from the microphone 105 to which the wireless communication terminal 200 responds, and further inputs a response operation by key input by the operation unit 106 or voice input by the microphone 105. The word input by voice and the response action input by voice or key are recorded in the recording unit 202. At this time, the feature amount of the voice input from the microphone 105 is measured by the measurement unit 201, and the feature amount is recorded in the recording unit 202 in association with the word and the response action as a reference value. After recording the response word and the response action, it is assumed that the wireless communication terminal 200 is placed in a place where outside light is blocked, for example, in a cage.

  The light detection unit 101 detects the intensity of external light from the time the power is supplied to the wireless communication terminal 200, and inputs the result to the control unit 102. The output value of the detection unit 101 changes. When the control unit 102 detects a change in the output value of the light detection unit 101, the control unit 102 gives an instruction to start the voice recognition processing to the voice recognition unit 107. At this time, if the response processing unit 109 does not respond during the time set by the timer 103, the voice recognition process is stopped.

  After the voice recognition unit 107 starts the voice recognition process, when voice is input from the outside to the microphone 105, that is, when the user makes a utterance, the voice recognition unit 107 performs voice recognition on the voice input from the microphone 105. Detects input speech words. At the same time, the measurement unit 201 measures the feature amount of the input voice. Then, the detected word and the measured voice feature amount are input to the collation unit 203. The collation unit 203 collates whether the input speech word and the feature amount match the word recorded in the recording unit 202 and are within the judgment criterion of the recorded feature amount. When the value is out of the value, a mismatch result is input to the control unit 102, and when the values match and are within the determination reference value, an ON signal is input to the response processing unit 109. When the ON signal is input from the collating unit 203, the response processing unit 109 receives at least one of the vibrator driving unit 109a, the LED driving unit 109b, and the speaker driving unit 109c based on the response operation registered in the recording unit 202. Is operated to vibrate the vibrator 111, turn on the LED unit 112, or reproduce the musical sound from the speaker 113 to notify the user of the location of the wireless communication terminal 200.

  As described above, according to the wireless communication terminal 200 of the present embodiment, the same operation and effect as the wireless communication terminal 100 of Embodiment 1 described above can be obtained, and the feature amount of the user's voice can be set at the time of word registration by voice. Since measurement and recording are performed, and this feature value is used as a criterion for speech recognition, it is possible to minimize the response to voices of people other than the user and ambient noise. That is, it is possible to obtain a speech recognition function with a lower error rate than in the case of collating only with words.

  The present invention has an effect that voice recognition processing can be started when there is a change in external light without operating a voice recognition dedicated key, and wireless communication such as a cellular phone, PHS, and PDA. Applicable to terminals.

1 is a block diagram showing a schematic configuration of a wireless communication terminal according to a first embodiment of the present invention. FIG. 2 is a block diagram showing a schematic configuration of a wireless communication terminal according to a second embodiment of the present invention. Block diagram showing a schematic configuration of a conventional mobile phone

Explanation of symbols

DESCRIPTION OF SYMBOLS 101 Light detection part 102 Control part 103 Timer 104,202 Recording part 105 Microphone 106 Operation part 107 Voice recognition part 108,203 Collation part 109 Response processing part 109a Vibration drive part 109b LED drive part 109c Speaker drive part 111 Vibrator 112 LED part 113 Speaker 201 Measuring unit

Claims (6)

Registration means for registering the keyed word and response action;
Voice input means for inputting voice;
Speech recognition means for recognizing a word input by the voice input means;
Light detection means for detecting light outside the device;
A response start instruction output means for giving an instruction to start voice recognition processing to the voice recognition means when there is a change in the output of the light detection means;
Collating means for collating the word registered in the registering means with the word recognized after being input by voice after the start of the speech recognition processing after the word is registered;
When the word registered in the registration unit matches the word recognized by voice input after the start of the speech recognition process based on the collation result by the collation unit, vibration, light, and music are performed according to the response operation registered in the registration unit. A response means for generating at least one of:
Wireless communication terminal equipped with. Voice input means for inputting voice;
Speech recognition means for recognizing a word input by the voice input means;
Registration means for registering the words and response actions recognized by the voice recognition means;
Light detection means for detecting light outside the device;
A response start instruction output means for giving an instruction to start voice recognition processing to the voice recognition means when there is a change in the output of the light detection means;
Collating means for collating the word registered in the registering means with the word recognized after being input by voice after the start of the speech recognition processing after the word is registered;
If the word registered in the registration unit matches the word recognized by voice input after the start of the speech recognition process based on the collation result by the collation unit, vibration, light, and music are performed according to the response operation registered in the registration unit. A response means for generating at least one of:
Wireless communication terminal equipped with. Voice input means for inputting voice;
Speech recognition means for recognizing a word input by the voice input means;
Voice feature quantity detecting means for detecting a feature quantity of the voice input by the voice input means;
Registration means for registering the word and response action recognized by the voice recognition means in association with the voice feature quantity detected by the voice feature quantity detection means;
Light detection means for detecting light outside the device;
A response start instruction output means for giving an instruction to start the voice recognition processing to the voice recognition means when there is a change in the output of the light detection means;
The word registered in the registration unit is compared with the word that is registered after the word is registered and is voice-input after the voice recognition process is started, and the voice that is input after the voice recognition process is started is checked. Collating means for collating whether or not the feature amount is within a criterion for determination of the feature amount of the voice registered in the registration unit;
Only when the speech word input after the start of the speech recognition process matches the registered word from the collation result by the collating unit and the feature amount of the speech is within the criterion, it is registered in the registration unit. Response means for generating at least one of vibration, light and music according to the response operation
Wireless communication terminal equipped with.   The wireless communication terminal according to claim 1, wherein the response unit generates vibration by driving a vibrator.   The wireless communication terminal according to any one of claims 1 to 3, wherein the response means generates light by driving a light emitting element.   The wireless communication terminal according to claim 1, wherein the response means generates a musical sound by driving a speaker.

Images