JPH07283857A - Voice dialing device - Google Patents

Abstract

PURPOSE:To accept a voice input such as cancellation even after the end of entry of a dial number and to start recognition automatically when talking is finished by terminating the recognition after the lapse of a prescribed time when an opposite party receives a call or the entry of a dial number is finished. CONSTITUTION:A relevant telephone number selection section 102 sends information representing a telephone number corresponding to a name being the result of recognition and information representing stop operation of phone call being the result of recognition to a telephone number transmission section 104. The telephone number transmission section 104 connects a line when the telephone number is received and interrupts the connection of the line when the information representing the stop of phone call is received. A line information detection section 107 checks whether or not an opposite party receives a phone call based on a line signal and when the opposite party receives the call, the information is sent to a recognition operation stop section 108 to stop the operation of a voice recognition section 101.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice dial device, and more particularly to the start and end of a voice recognition operation.

[0002]

2. Description of the Related Art A voice dial device is very convenient because a user does not need to remember a telephone number having many digits, and the user can make a call by voice inputting the name of the other party. Also,
Compared with the speed dial, the number of phone numbers that can be registered in the speed dial is at most 2,30, whereas the voice dialing device can recognize several hundred to several thousand words at a time with the current voice recognition technology. There are advantages.

In constructing a voice dial device, voice recognition may cause erroneous recognition, and therefore it is necessary to devise a method for preventing the voice dial device from malfunctioning.

An example of a conventional voice dial is disclosed in Japanese Patent Laid-Open No. Sho 60.
No. 0855655. The voice dial device described in this publication considers preventing the malfunction of the dial number input completion by ending the voice recognition operation after the dial number input is completed.

[0005]

However, in this conventional voice dial device, when the voice recognition result is an erroneous recognition, the user tries to cancel the dial number input by the voice recognition due to the erroneous recognition formula. However, since voice recognition does not work after the dial number is entered, it is necessary to enter a button to cancel it. In addition, when the voice dial is used again after the call ends, it becomes necessary to input a button for starting the recognition operation.

[0006]

In order to solve the above-mentioned problems, a voice dial device according to the first invention of the present application,
A voice recognition means for recognizing the input voice and outputting the recognition result;
A telephone number storage means for storing a telephone number, a means for selecting a telephone number in the telephone number storage means from the recognition result of the voice recognition means, a transmission means for transmitting the telephone number, and a communication means for making a call. In the voice dial device consisting of means, line information detecting means for detecting the start of a call,
Means for controlling the operation of the voice recognition means using the output of the line information detection means.

Further, the voice dial device according to the second invention of the present application is characterized in that, in addition to the first invention of the present application, when the calling party is talking, the information is detected from a telephone line. And the line information detecting means.

The voice dial device according to the third aspect of the present invention includes a voice recognition means for recognizing an input voice and outputting a recognition result, a telephone number storage means for storing a telephone number, and the voice recognition means. In a voice dial device including a means for selecting a telephone number in the telephone number storage means from the recognition result, a transmitting means for transmitting the telephone number, and a means for making a call, after the transmitting means makes a call, It is provided with an elapsed time measuring means for measuring the elapsed time and outputting the information when a predetermined fixed time has elapsed, and means for controlling the operation of the voice recognition means from the output of the elapsed time measuring means.

Further, in addition to the first, second and third inventions of the present application, the voice dial device according to the fourth invention of the present application includes the line information detecting means for detecting the end of a call, and the line information detection. Means for controlling the operation of the voice recognition means based on the output of the means.

[0010]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a voice dial device according to the present invention will be described with reference to the drawings.

First, an embodiment according to the first invention of the present application will be described. FIG. 1 is a block diagram showing an embodiment according to the first invention of the present application.

FIG. 4 shows an example of the stored contents of the telephone number storage unit 103 of this embodiment.

Referring to FIG. 1, a first embodiment of the present invention is a voice recognition unit 101 for recognizing a voice input by a user.
A corresponding telephone number selection unit 102 that outputs the corresponding telephone number from the recognition result, a telephone number storage unit 103 that stores the telephone number, a telephone number transmission unit 104 that transmits the telephone number to the line, and a user Telephone 105 used when talking on the telephone, and recognition result display unit 1 for displaying the recognition result
06, a line information detection unit 107 for extracting information such as the other party who made a call from the telephone line has started a call, is calling the other party, or has hung up the other party, and a function for stopping the voice recognition operation. The recognition operation stopping unit 108 having

Next, the operation of this embodiment will be described with reference to FIG. In the voice recognition unit 101, the voice input by the user is converted into a digital signal, the time series of the feature vector is obtained, the pattern matching is performed with this and the standard pattern prepared in advance, and the voice recognition result is created. Corresponding telephone number selection unit 102, recognition result display unit 1
It outputs to 06. The recognition result display unit 106 displays the recognition result to the user. Corresponding telephone number selection unit 102,
Based on the name of this recognition result, the corresponding telephone number is checked from the contents stored in the telephone number storage unit 103, and this telephone number is sent to the telephone number sending unit 104. Further, if the information for stopping the operation of making a call at the time of erroneous recognition such as a predetermined “cancel” is sent as the recognition result, the information for stopping the operation of making a call is provided to the telephone number sending unit 104. Send to. When the telephone number is sent from the corresponding telephone number selecting unit 102, the telephone number sending unit 104 sends a dial signal of this telephone number to the telephone line to connect the line. Further, the telephone number sending unit 104 disconnects the telephone line when the corresponding telephone number selecting unit 102 receives information for stopping the operation of making a call. The line information detection unit 107 detects the start of the call from the signal of the telephone line, and if the call is started, sends the information to the recognition operation stop unit 108. As the detection of the call start, for example,
It can be performed by eliminating the ringing tone or detecting the human voice. The recognition operation stopping unit 108 stops the operation of the voice recognition unit 101 based on this information, thereby preventing the voice recognition from malfunctioning due to the user's call, ambient noise, or the like. After connecting the line, the user talks on the telephone 105.

Next, a specific example will be described.

In the voice recognition unit, for example, "Manager Sato",
"Suzuki section manager", "Tanaka section chief", "Saito section chief", "Endo section chief", "cancellation" are recognized. At this time, it is assumed that the user voice-inputs "Manager Sato". At this time,
The voice recognition unit 101 performs voice recognition on this voice input, and if the recognition is correctly performed, the recognition result “Manager Sato” is sent to the corresponding telephone number selection unit 102, and the recognition result display unit 106 notifies the user of the recognition result. "Manager Sato" is displayed. Corresponding telephone number selection unit 102 checks the telephone number corresponding to the name of the recognition result from the contents stored in telephone number storage unit 103. When the content of the telephone number storage unit 103 is as shown in FIG. 4, for example, it can be seen that the telephone number corresponding to the recognition result “Manager Sato” is “1234”. The telephone number sending unit 104 transmits the dial signal of the telephone number "1234" to the telephone line and connects the line. After the line is connected, if the line information detecting unit 107 detects that the other party answers the telephone, the recognition operation stopping unit 108 stops the operation of the voice recognition unit 101. When the other party answers the call, the user talks on the telephone 105.

It is also assumed that when the user voice-inputs "Manager Sato", the voice recognition unit 101 makes an erroneous recognition and "Tanaka Chief" is sent to the corresponding telephone number selection unit 102 as a recognition result. At this time, the user confirms the recognition result by the output of the recognition result display unit 106, and when it is found that the recognition result is incorrect, the user inputs “cancel” by voice into the system. Since the voice recognition unit 101 is operating until the other party answers the telephone, the corresponding telephone number selection unit 102 sends this information to the telephone number transmission unit 104 if "cancel" is recognized. The telephone number sending unit 104 disconnects the telephone line connection.

Next, an embodiment according to the second invention of the present application will be described. A block diagram showing an embodiment according to the second invention of the present application is the same as the first embodiment shown in FIG.

The operation of this embodiment will be described with reference to FIG.

Voice recognition section 101, corresponding telephone number selection section 1
02, telephone number storage unit 103, telephone number transmission unit 104,
Since the operations of the telephone 105 and the recognition result display unit 106 are the same as those in the first embodiment, their description will be omitted.

In this embodiment, the line information detecting section 107
The call start is detected from the signal of the telephone line, and if the call is started, the information is sent to the recognition operation stopping unit 108.
If the other party is busy, the recognition operation stopping unit 10
The information is sent to 8, and the recognition operation is stopped. Whether or not the other party is busy can be checked, for example, by detecting a signal on the line when the other party is busy.
At this time, the connection of the telephone line may be disconnected and the call may be terminated.

Next, an embodiment according to the third invention of the present application will be described. FIG. 2 is a block diagram showing an embodiment according to the third invention of the present application.

Referring to FIG. 2, the third embodiment of the present invention recognizes a voice input by a user as a voice recognition unit 201.
A corresponding telephone number selection unit 202 that outputs a corresponding telephone number from the recognition result, a telephone number storage unit 203 that stores the telephone number, a telephone number transmission unit 204 that transmits the telephone number to the line, and a user A telephone 205 used for telephone conversation and a recognition result display unit 2 for displaying a recognition result
06, an elapsed time measuring unit 207 that measures an elapsed time after the telephone number is sent to the line, and a recognition operation stopping unit 208 that has a function of stopping the voice recognition operation.

Next, the operation of this embodiment will be described with reference to FIG. In the voice recognition unit 201, the voice input by the user is converted into a digital signal, the time series of the feature vector is obtained by analysis, the pattern matching is performed with the standard pattern prepared in advance, and the voice recognition result is created. Corresponding telephone number selection unit 202, recognition result display unit 2
It outputs to 06. The recognition result display unit 206 displays the recognition result. Corresponding telephone number selecting section 202 determines the corresponding telephone number from the name of the recognition result as telephone number storing section 203.
The telephone number is sent to the telephone number sending unit 204 by checking from the contents stored in. Further, if the information for stopping the operation for making a call at the time of erroneous recognition such as a predetermined “cancel” is sent as the recognition result, the information for stopping the operation for making a call is provided to the telephone number sending unit 20.
Send to 4. When the telephone number is sent from the corresponding telephone number selection unit 202, the telephone number sending unit 204 sends a dial signal of this telephone number to the telephone line to connect the line. Further, the telephone number sending unit 204 is the corresponding telephone number selecting unit 202.
The connection of the telephone line is disconnected when the information to stop the operation to make a call from is sent from. Elapsed time measuring unit 20
7 measures the elapsed time after the telephone number sending unit 204 sends a dial signal of the telephone number to the telephone line, and when the preset time has passed, sends the information to the recognition operation stopping unit 208. The recognition operation stopping unit 208 stops the operation of the voice recognition unit 201 based on this information, thereby preventing the voice recognition from malfunctioning due to the user's call, ambient noise, or the like. After the line is connected, the user can use the telephone 205
To call.

Next, a specific example will be described.

In the voice recognition unit, for example, "Sato section manager",
It is assumed that "Manager Suzuki", "Manager Tanaka", "Manager Saito", "Manager Endo", and "Cancel" are recognition targets, and the user inputs "Manager Sato" by voice. At this time, the voice recognition unit 201 performs voice recognition on the voice input, and if the recognition is performed correctly, the recognition result “Manager Sato” is sent to the corresponding telephone number selection unit 202, and the recognition result display unit 206 notifies the user. Display the recognition result "Manager Sato". Corresponding telephone number selecting section 202 checks the corresponding telephone number from the contents stored in telephone number storing section 203 from the name of the recognition result. When the content of the telephone number storage unit 203 is as shown in FIG. 1, for example, it can be seen that the telephone number corresponding to the recognition result “Manager Sato” is “1234”. The telephone number sending unit 204 transmits the dial signal of the telephone number "1234" to the telephone line and connects the line. Also, when the telephone number sending unit 204 connects the line, it sends information about this connection to the elapsed time measuring unit 207. The elapsed time measuring unit 207 measures the time since this information was sent, and sends the information that the fixed time has been measured to the recognition operation stopping unit 208 if the preset fixed time has passed. When the recognition operation stopping unit 208 receives this information, the recognition operation stopping unit 208 stops the operation of the voice recognition unit 201. When the other party answers the call, the user talks on the telephone 205.

It is also assumed that when the user voice-inputs "Manager Sato", the voice recognition unit 201 makes an erroneous recognition and "Tanaka Chief" is sent to the corresponding telephone number selection unit 202 as a recognition result. At this time, the user confirms the recognition result by the output of the recognition result display unit 206, and if the user recognizes that the recognition result is incorrect, the user inputs "cancel" by voice. If it is within a certain time preset by the elapsed time measuring unit 207, the voice recognition unit 201 is operating. Therefore, if “cancel” is recognized, the corresponding telephone number selection unit 202 sends this information to the telephone number. Send to section 204. The telephone number sending unit 204 disconnects the telephone line connection.

Next, an embodiment according to the fourth invention of the present application will be described. FIG. 3 is a block diagram showing an embodiment according to the fourth invention of the present application.

Referring to FIG. 3, the fourth embodiment of the present invention is different from the first embodiment shown in FIG. 1 in that a recognition operation starting unit 309 is provided. Voice recognition unit 301, corresponding telephone number selection unit 302, telephone number storage unit 303, telephone number transmission unit 304, telephone 305, recognition result display unit 306,
Since the operation of the recognition operation stopping unit 308 is the same as that of the first embodiment, the description thereof will be omitted.

In this embodiment, the line information detecting unit 307 detects the information that the user or the called party hangs up after the call ends, and recognizes this information.
Send to. As a method of detecting the information when the telephone is hung up, for example, a method of checking whether or not there is a signal on the line in a state where no call is being made and a detection of a human voice are considered.

Upon receiving this information, the recognition operation starting unit 309 sends a command for starting the recognition operation to the voice recognition unit 301. The voice recognition unit 301 activates the recognition operation when receiving this command.

Thus, when the voice dial is used again after the call ends, it is not necessary to input a button for starting the recognition operation.

In the first, second, third, fourth and fifth embodiments, the recognition result is displayed, but it may be presented to the user by voice information such as voice synthesis.

[0034]

As described above, according to the present invention, in the voice dial device, the recognition operation is terminated when the other party answers the telephone, after a certain time has elapsed after the completion of the dial number input, or when the other party is talking. By doing so, the recognition operation can be performed even after the dial number is entered, and voice input such as cancellation can be accepted, and the recognition operation can be automatically started without button input after the call is ended. Therefore, there is an effect that labor such as button input can be saved, malfunctions due to misrecognition can be reduced, and usability for the user can be improved.

[Brief description of drawings]

FIG. 1 is a configuration diagram showing an embodiment according to first and second inventions of the present application.

FIG. 2 is a configuration diagram showing an embodiment according to a third invention of the present application.

FIG. 3 is a configuration diagram showing an embodiment according to a fourth invention of the present application.

FIG. 4 is a diagram illustrating processing in the first, second, third, and fourth inventions of the present application.

[Explanation of symbols]

 101 voice recognition unit 102 corresponding telephone number selection unit 103 telephone number storage unit 104 telephone number transmission unit 105 telephone 106 recognition result display unit 107 line information detection unit 108 recognition operation stopping unit 201 voice recognition unit 202 corresponding telephone number selection unit 203 telephone number Storage unit 204 Telephone number sending unit 205 Telephone 206 Recognition result display unit 207 Elapsed time measuring unit 208 Recognition operation stopping unit 301 Voice recognition unit 302 Corresponding telephone number selection unit 303 Telephone number storage unit 304 Telephone number sending unit 305 Telephone 306 Recognition result display Part 307 Line information detecting part 308 Recognition operation stopping part 309 Recognition operation starting part

Claims (4)

[Claims] 1. A voice recognition means for recognizing an input voice and outputting a recognition result, a telephone number storage means for storing a telephone number, and a telephone number in the telephone number storage means based on the recognition result of the voice recognition means. In the voice dial device including a means for selecting, a calling means for sending the telephone number, and means for making a call, line information detecting means for detecting the start of a call and output of the line information detecting means are used. And a means for controlling the operation of the voice recognition means. 2. The voice dial device according to claim 1, wherein the line information detecting means detects the information from a telephone line when the calling party is busy. 3. A voice recognition means for recognizing an input voice and outputting a recognition result, a telephone number storage means for storing a telephone number, and a telephone number in the telephone number storage means based on the recognition result of the voice recognition means. In a voice dial device comprising a means for selecting, a calling means for sending the telephone number, and means for making a call, a predetermined fixed time is measured by measuring the elapsed time after the calling means makes a call. A voice dial device comprising: elapsed time measuring means for outputting the information when the time has elapsed; and means for controlling the operation of the voice recognizing means by the output of the elapsed time measuring means. 4. The line information detecting means for detecting the end of a call, and the means for controlling the operation of the voice recognition means based on the output of the line information detecting means. The voice dial device described in 2 and 3.