JP3278595B2 - mobile phone - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a mobile phone, and more particularly to a mobile phone capable of realizing a part of the function of the mobile phone by voice using a voice recognition function.

[0002]

2. Description of the Related Art An example of a conventional portable telephone having a voice recognition function is disclosed in Japanese Patent Laid-Open No. 3-45057.

FIG. 4 is a block diagram of a portable telephone having a conventional voice recognition function disclosed in Japanese Patent Application Laid-Open No. 3-45057.

In FIG. 4, reference numeral 1 denotes a voice input unit for inputting a voice by a user of a portable telephone such as a microphone, 2 denotes voice analysis means for extracting a feature amount of voice input from the voice input unit 1, and 3 denotes a speaker. It is.

[0005] Reference numeral 4 denotes a voice synthesizing unit for generating the name and the like as a voice feature amount for confirming that the telephone number and the name of the other party output from the search processing unit 8 have been received, and outputting to the speaker 3. is there.

Reference numeral 5 denotes a display unit, and reference numeral 6 denotes a dial number sending unit for dialing the telephone number of the other party.

[0007] In a registration state, the feature amount extracted by the voice analysis means 2 is registered in the voice standard pattern memory 10 as a voice standard pattern in the registration state, and the input voice pattern and the voice standard pattern are compared in the recognition state. , Which outputs information such as the address of the closest standard pattern.

Reference numeral 8 denotes information such as the address output by the voice recognition means 7 and information from the key information input section 9 for registering information such as the telephone number and name of the other party in the information memory 11, 11 is a search processing section for performing a search and outputting information such as the telephone number and name of the other party to the display section 5, the voice synthesis section 4, and the dial number transmission section 6.

Reference numeral 9 denotes a key information input unit for inputting a telephone number and a character string in a registration state.

Reference numeral 10 denotes a voice standard pattern memory registered as standard voices indicating a plurality of destinations for dial transmission of each caller, and reference numeral 11 denotes an information memory for telephone numbers and names of required destinations. Both the voice standard pattern memory 10 and the information memory 11 are external memory card 1
2 included.

Next, the operation of the conventional example will be described with reference to FIG.

First, at the time of registration for registering the voice of the memory card user, when the name of the other party is input by voice from the voice input unit 1, the voice analysis means 2 extracts the characteristic amount of the input voice pattern. After the voice recognition means 7 having received this confirms that the same voice feature has not been registered in the voice standard pattern memory 10, the registration standby state for registering the voice feature in the voice standard pattern memory 10. Becomes At the same time, information such as an address is output to the search processing unit 8.

At this time, the information such as the telephone number and the name of the other party inputted from the key information input section 9 is displayed on the display means 5 via the search processing section 8, and after visually confirming the information, the memory-in key is pressed. When the button is pressed, the information such as the telephone number and name is registered in the information memory 11 and the audio standard pattern in the registration standby state is registered in the audio standard pattern memory 10.

Next, in the case of recognizing the voice of the caller and performing automatic dialing, when the voice input unit 1 inputs the name of the other party by voice, the voice analysis unit 2 extracts the feature amount of the voice pattern input. The voice recognition means 7 accepts the search, searches the voice standard pattern memory 10 for the closest voice feature amount, and outputs information such as its address to the search processing unit 8.

The search processing unit 8 searches the information memory 11 for information such as the telephone number and name of the other party based on the information such as the address. Also, the searched voice feature is transferred to the voice synthesizing means 4 and then transmitted to the speaker 3 as a voice signal, and a positive voice is emitted if the name of the reception confirmation is received from the speaker 3 and an erroneous search is made if the search is incorrect. Emits a voice.
If incorrect, the same operation is performed again. If correct, the voice is received by the voice input unit 1, received by the voice recognition unit 7 via the voice analysis unit 2, and the destination telephone number is transmitted to the dial number transmission unit 6. Output and dialing is performed.

[0016]

A first problem of the prior art is that words to be recognized when performing voice recognition must be recorded in advance. For this reason, the user of the mobile phone must register the voice every time the number of recognized words is increased. In addition, since the environment at the time of recording affects the recognition rate, there is a problem that a new recognized word cannot always be registered at any place.

A second problem is that words to be recognized when voice recognition is performed are recorded in advance, but recognition processing is performed on voice features of the recorded words.
For this reason, only the speaker who has registered the recognition word can use the voice recognition function, and even if a person other than the registered speaker utters a voice, the recognition process is not performed properly and the voice recognition function can be used. Can not.

A third problem is that if the recognition result is correct with respect to the recognition word and the voice for confirming the reception, a positive voice is emitted, and if the recognition result is incorrect, an erroneous voice is generated. For this reason, the user of the mobile phone must always input the voice twice, that is, the name of the destination and the voice for confirmation when performing the voice recognition processing.

The present invention has been made in view of the above points, and provides a more user-friendly mobile phone capable of operating the mobile phone by voice even in a situation where the user of the mobile phone cannot use his / her hand. The purpose is to:

[0020]

SUMMARY OF THE INVENTION The present invention solves the above-mentioned first and second problems of the prior art by using a name of a memory dial or a function name of a portable telephone as a recognition word. Therefore, there is no need to newly register voice. In addition, since recognition processing is performed not on a specific word but on a character, a plurality of persons can use the voice recognition function, not limited to a specific speaker.

Further, the present invention solves the third problem of the prior art described above, by recognizing the name of the destination, and then performing a key operation corresponding to the recognition result.
When the recognition result is correct, an operation corresponding to the recognition result is performed, and when the recognition result is incorrect, malfunction is prevented.

In the present invention, a name registered in a memory dial of a mobile phone is used as a recognition word. In addition, a recognition word is prepared in advance to operate a specific function of the mobile phone other than the memory dial. After the recognition result is determined, the recognition result is displayed on a display unit such as an LCD, and a response voice is output.
When the recognition result is correct, the operation corresponding to the recognition result is performed, and when the recognition result is incorrect, the operation corresponding to the recognized word is stopped.

[0023]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram of a mobile phone according to an embodiment of the present invention.

The mobile phone includes a radio unit 21 for transmitting and receiving radio signals to and from a base station (not shown), an operation unit 22 for operating the mobile phone, a display unit 23 for displaying numbers, characters, and the like to the user. It incorporates a data ROM 24 for storing fixed recognition words for voice recognition and data for response voice, a main control unit for controlling the entire mobile phone, and a DSP for performing voice data processing such as compression and decoding of voice data. LSI25,
Speech recognition L that performs speech recognition processing on input speech
The connection between the SI 26 and the A / D converter 28 is LS
A switch 27 for switching between I25 and a speech recognition LSI 26, an A / D converter 28 for converting between analog data and digital data, a microphone 29 for inputting speech data to be subjected to speech recognition, And a receiver 30 that outputs a response voice.

Next, an operation process of the mobile phone shown in FIG. 1 will be described.

The user of the mobile phone registers the name and the telephone number of the memory dial from the operation unit 22 using the memory dial registration function of the mobile phone. Voice recognition LSI
26 does not operate during normal operation, and when performing voice recognition processing, the user of the mobile phone presses a key of the operation unit 22 for detecting the start of voice recognition processing. When the main control unit of the LSI 25 detects that the speech recognition start key is pressed, the data ROM 2
4 or the inside of the LSI 25 to transmit the recognition word data to the speech recognition LSI 26, and the speech recognition LSI 2
Then, a voice recognition start command is transmitted to 6 to start voice recognition processing. In addition, the display unit 23 displays that the voice recognition process is being performed in order to notify the user of the mobile phone that the voice recognition process has started and that the mobile phone is waiting for a voice input.

When the user of the portable telephone starts the speech recognition processing, he speaks the words to be recognized toward the microphone 29. The input voice is converted into digital data by the A / D converter 28 and input to the voice recognition LSI 26. The voice input LSI 26 performs voice recognition processing on the input data, and when the recognition result is determined, transmits the recognition result to the main control unit of the LSI 25. The main control unit of the LSI 25 displays data corresponding to the recognition result on the display unit 23.
And a response voice corresponding to the recognition result is displayed on the receiver 30.
Output from

The response voice corresponding to the recognition word is a data R
The response voice corresponding to the recognition result is read from the data ROM 24 and output by the LSI 25. The response voice data is prepared in advance by data compressed by ADPCM, decoded by the ADPCM decoding function of the voice recognition LSI 26, and output to the A / D converter 28.
D / A conversion is performed by the D converter 28, and a response voice is output from the receiver 30.

When the name of the memory dial is used as a recognition word, the response voice word is an arbitrary word. Therefore, data of a single tone is prepared in the data ROM 24, and when the recognition result is the name of the memory dial, A single sound corresponding to the name is connected and decoded, and a response voice is output.

When the recognition word is a fixed word such as a function function, fixed data is prepared in advance and output as a response voice.

When the recognition result is correct, an operation corresponding to the recognition result is performed. When the recognition result is incorrect, the operation corresponding to the recognition result is stopped by pressing a specific key from the operation unit 22.

For example, when it is desired to make a call to a name registered in the memory dial, a voice recognition processing start key is pressed from the operation unit 22 and the name is uttered from the microphone 29. When the spoken name is recognized by the voice recognition LSI 26, the recognized name is displayed on the display unit 23, and the recognized name is output from the receiver 30 as a response voice, and is transmitted to a telephone number corresponding to the name of the recognition result. .

Further, it is assumed that the setting of automatic / manual transmission switching can be performed by the operation unit 22 using the function function.
In the above-described embodiment, the case of automatic transmission has been described. However, when the transmission is set to manual transmission, the recognition result is determined, the response voice is output, and the start key is pressed from the operation unit 22 to respond to the recognition result. Actions can be taken.

Next, the operation of this embodiment will be described with reference to the flowcharts of FIGS.

FIG. 2 is a flowchart of the voice recognition process according to the present embodiment.

FIG. 3 is a flowchart of the voice recognition process according to the present embodiment, and is a part following FIG.

The user of the portable telephone registers the name and telephone number of the called party in the memory dial regardless of the voice recognition function (S-1). The user of the voice recognition function using the voice recognition function selects and sets either automatic transmission or manual transmission (S-2). At the time of automatic transmission setting, after the recognition result is determined, the time until transmission is set.

When using the voice recognition function, the user of the mobile phone detects the start of the voice recognition process by pressing the voice recognition start key from the operation unit 22 (S-3).

After the start of the voice recognition process is detected, the start of the voice recognition process is displayed on the display unit 23, and the voice recognition LSI 2
In step 6, the recognition dictionary is read (S-4). The recognition dictionary reads fixed recognition words such as words of a function of a mobile phone, and name data of a memory dial assigned for voice recognition by a user of the mobile phone. After setting the recognition process, the user of the mobile phone,
A word corresponding to the function of the mobile phone to be operated is uttered from the microphone 29 (S-5).

The main controller of the LSI 25 starts the timer 1 after the start of the recognition process (S-6). This timer 1 has a predetermined time, e.g.
If the recognition result cannot be determined (S-8) even after the lapse of seconds (S-7), the recognition process is stopped (S-16).

The voice recognition LSI 26 performs a recognition process on the input voice, and the main control unit of the LSI 25 reads out the confirmed data of the recognition result from the voice recognition LSI 26 (S-8).

After the recognition result is determined by the main control unit of the LSI 25, the recognition result is displayed on the display unit 23 such as an LCD (S-
9) Output a response voice corresponding to the recognition result (S-1)
0).

Next, in step (S-2), it is checked whether or not automatic transmission is set (S-11). When automatic transmission is set, the timer 2 is started (S-1).
2). At the time of automatic call setting, the user of the mobile phone confirms whether or not the recognition result is correct from the response voice. If the recognition result is incorrect, before the timer 2 times out (S-14), the end key is transmitted from the operation unit 22. And press (S-1
3) Stop calling other than the target telephone number (S-17). When the user of the mobile phone determines from the response voice that the recognition result is correct, the timer 2 times out (S-14), and a call is made to the telephone number corresponding to the recognition result (S-15).

In step (S-11), if the manual transmission is set in step (S-2), the user of the mobile phone confirms from the voice response whether or not the recognition result is correct (step S-11). If the recognition result is correct (S-18), the start key is pressed (S-19), and a call is made to the telephone number corresponding to the recognition result (S-20). In step (S-18), when the recognition result is wrong, the user of the mobile phone presses the end key from the operation unit 22 (S-2).
1) Recognition processing ends with the result of the recognition going away (S)
-22).

In the above description of the operation, an example of transmission of a memory dial has been described. However, when the function is performed after recognition, the function is called after the recognition result is determined regardless of the automatic / manual setting.

Although one embodiment of the present invention has been described above, the present invention is not limited to this embodiment.
Various modifications are possible according to the spirit of the invention.

[0048]

The first effect is that a plurality of persons can use the voice recognition function.

The reason is that the user of the mobile phone does not utter and register the recognition word, and the fixed word prepared in advance is used.
This is because words registered in the memory dial are used as recognition words.

The second effect is that the user of the mobile phone can use his favorite words as recognition words.

The reason is that the data of the name registered in the memory dial is used as a recognition word.

The third effect is that when performing the voice recognition process,
The ability to make a phone call to a target party simply by speaking a single recognition word.

The reason is that after a voice is uttered, a response voice is output, and when the spoken word and the response voice match, after a few seconds elapse with a timer or a telephone number corresponding to the name recognized by pressing a key, a call is made. It is possible to call.

The fourth effect is that the user of the portable telephone can realize the intended operation by the voice recognition function without performing a malfunction.

The reason is that by outputting the recognition result as a response voice, when the recognition result is incorrect, the end key can be pressed to prevent malfunction.

[Brief description of the drawings]

FIG. 1 is a block diagram of a mobile phone according to an embodiment of the present invention.

FIG. 2 is a diagram showing a flowchart of a speech recognition process in the present embodiment.

FIG. 3 is a diagram illustrating a flowchart of a speech recognition process according to the present embodiment, and is a diagram illustrating a portion that follows FIG. 2;

FIG. 4 is a block diagram of a conventional mobile phone having a voice recognition function disclosed in Japanese Patent Application Laid-Open No. 3-45057.

[Explanation of symbols]

 Reference Signs List 1 voice input unit 2 voice analysis unit 3 speaker 4 voice synthesis unit 5 display unit 6 dial number transmission unit 7 voice recognition unit 8 search processing unit 9 key information input unit 10 voice standard pattern memory 11 information memory 21 radio unit 22 operation unit 23 Display unit 24 Data ROM 25 LSI 26 Voice recognition LSI 27 Switch 28 A / D converter 29 Microphone 30 Receiver

──────────────────────────────────────────────────続 き Continued on the front page (58) Field surveyed (Int.Cl. ⁷ , DB name) H04M 1/27 H04Q 7/38

Claims (2)

(57) [Claims] In a mobile phone having a voice recognition function, a user of the mobile phone presses a voice recognition start key to start a voice recognition process, and then speaks, and recognizes the spoken voice by voice recognition. results after confirmation, comprising a notification means for notifying the recognition result to the user of the mobile phone, the notification
Means that the recognition result is used for voice recognition in the memory dial
When the name is assigned, it is used as voice response data.
Prepare single sound data, and use the
Connects single notes corresponding to names assigned for voice recognition
And output a voice response from the receiver.
In the case of the function function, the response voice data and
Prepare fixed voice data in advance, and
And a means for outputting from a receiver . 2. A mobile phone having a voice recognition function, wherein the user of the mobile phone presses a voice recognition start key to start a voice recognition process and then speaks, and the spoken voice is recognized by voice recognition. results after confirmation, comprising a notification means for notifying the recognition result to the user of the mobile phone, the notification
Means that the recognition result is used for voice recognition in the memory dial
When the name is assigned, it is used as voice response data.
Prepare single sound data, and use the
Connects single notes corresponding to names assigned for voice recognition
And output a voice response from the receiver.
In the case of the function function, the response voice data and
Prepare fixed voice data in advance, and
And output from the receiver when automatic calling is set.
In some cases, the user of the mobile phone
Check if the recognition result is correct, and
Time out, the phone number corresponding to the recognition result
Mobile phone, characterized in that the transmission.