JP2003006208A - Voice recording apparatus and method, voice reproducing apparatus and method, voice recording and reproducing system and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To more rapidly retrieve necessary information from recorded voice. SOLUTION: Voice data inputted from a voice input part 4 of a voice recording apparatus 1 and stored in a voice storage 5 are split in each utterance by a split processing part 6, and the time position of each utterance is calculated. When a voice recognition part 9 detects in the split voice data the same keyword with what stored in a keyword storage 8, makes the keyword a tag, attaches the importance of the tag and the keyword to the voice data and stores the data in a data save area 10 in chronological order. A data reception part 25 of a voice reproducing apparatus 21 receives supply of data from the voice recording apparatus 1 and store the data in a data storage 26. A tag display part 27 displays the tags color coded and stored in the data storage 26 in chronological order. The data storage 26 outputs the voice data on and after the time position of the tag selected by the user in the voice output part 29 and reproduces the data as voice.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an audio recording apparatus and method, an audio reproducing apparatus and method, an audio recording / reproducing system and method, and more particularly to an audio recording capable of quickly retrieving necessary information from recorded audio. The present invention relates to an apparatus and method, an audio reproducing apparatus and method, an audio recording / reproducing system and method.

[0002]

2. Description of the Related Art For example, in a mail-order sales using a telephone, a receptionist presents a manualized instruction to a customer, and based on the answer from the customer, the content of the call, the number of the product the customer purchases, Efficiently extract the necessary information such as color and size, and inform the delivery staff. The person in charge of delivering the product delivers the product as requested by the customer based on the information.

[0003]

However, if such a conventional reception method is applied when individual call contents are different, such as a question, a request, or a complaint from a customer, it is usually Since the receptionist does not have specialized knowledge, there is a problem that it is difficult to extract necessary information and accurately convey the information to the third party. Furthermore, for example, when the information is transmitted to the secondary person in charge or the third person in charge, it is more difficult for the final person in charge to acquire the necessary information. It is also possible that the voice recording / playback device records all the call contents and the final person in charge listens to all the recorded call contents, but doing so has the problem of taking too much time. It was

The present invention has been made in view of such a situation, and a tag is added to a voice based on a keyword and stored, and the stored tags are classified according to priority and displayed in chronological order. Makes it possible to search for the target recorded content more quickly, and in turn, from the recorded content,
This is to enable the necessary information to be retrieved quickly and accurately.

[0005]

A voice recording apparatus according to the present invention includes a dividing means for dividing voice data, a keyword extracting means for extracting a keyword from the voice data divided by the dividing means, and a keyword extracting means for extracting the keyword. It is characterized by further comprising: an adding unit for adding a tag to the audio data divided by the dividing unit based on the keyword, a tag list, and a transmitting unit for transmitting the audio data to the audio reproducing device.

Voice input means for inputting voice, voice storage means for storing voice data input by the voice input means, time position storage means for storing the time position of the voice data divided by the dividing means, and a keyword The method further comprises: a keyword storage means for storing the data; and a receiving means for receiving a request from the audio reproducing device. The dividing means divides the audio data stored by the audio storage means, and the keyword extracting means stores the audio data by the keyword storage means. The transmitting means can transmit the list of tags and the voice data in response to the request from the voice reproducing device.

It is possible to further include a storage unit that stores the tags by distinguishing them according to the priority of the keyword.

The storage means can sort and store tags in time series.

The voice recording method of the present invention comprises a dividing step for dividing voice data, a keyword extracting step for extracting a keyword from the voice data divided by the processing of the dividing step, and a keyword extracted by the processing of the keyword extracting step. Based on the above, the method further includes an adding step of adding a tag to the audio data divided by the processing of the dividing step, a tag list, and a transmitting step of transmitting the audio data to the audio reproducing device.

The audio reproducing apparatus of the present invention includes a list receiving means for receiving a list of tags transmitted from the audio recording apparatus, and a display means for displaying the list of tags received by the list receiving means in a time series. Selection means for selecting a predetermined tag from the list of tags displayed by the display means, and request means for requesting the audio recording device to transmit audio data corresponding to the time position of the tag selected by the selection means. And audio data receiving means for receiving the audio data requested by the requesting means from the audio recording device, and reproducing means for reproducing the audio data received by the audio data receiving means.

The display means can display the tags by distinguishing them according to the priority.

The audio reproducing method of the present invention includes a list receiving step of receiving a list of tags transmitted from the audio recording device, and a display step of displaying the list of tags received by the processing of the list receiving step in chronological order. And a voice recording of a selection step for selecting a predetermined tag from the list of tags displayed by the processing of the display step and transmission of voice data corresponding to the time position of the tag selected by the processing of the selection step. A request step for requesting the apparatus, a voice data receiving step for receiving the voice data requested by the processing of the request step from the voice recording apparatus,
And a reproduction step of reproducing the audio data received by the processing of the audio data receiving step.

According to the audio recording / reproducing system of the present invention, the audio recording device is configured such that by the keyword extracting means for extracting a keyword from the audio data divided by the dividing means, and the dividing means by the keyword extracting means. The audio reproducing device includes an adding means for adding a tag to the divided audio data, a list of tags, and a transmitting means for transmitting the audio data to the audio reproducing device, and the audio reproducing device stores the list of tags transmitted from the audio recording device. List receiving means for receiving, display means for displaying a list of tags received by the list receiving means in chronological order, selection means for selecting a predetermined tag from the list of tags displayed by the display means, Requesting means for requesting the audio recording device to transmit audio data corresponding to the time position of the tag selected by the selecting means , A voice data receiving means for receiving from the voice recorder audio data requested by the request means,
And a reproducing means for reproducing the audio data received by the audio data receiving means.

A voice recording / reproducing method of the present invention is a voice recording method of a voice recording device, comprising a dividing step of dividing voice data, and a keyword extracting step of extracting a keyword from the voice data divided by the processing of the dividing step.
Based on the keyword extracted by the processing of the keyword extraction step, an adding step of adding a tag to the audio data divided by the processing of the dividing step, a list of tags, and a step of transmitting the audio data to the audio reproducing device. The audio reproducing method of the audio reproducing device includes a list receiving step of receiving a list of tags transmitted from the audio recording device, and a display step of displaying the list of tags received by the process of the list receiving step in chronological order. And a voice recording of a selection step for selecting a predetermined tag from the list of tags displayed by the processing of the display step and transmission of voice data corresponding to the time position of the tag selected by the processing of the selection step. Voice recording of required steps required by the device and voice data requested by the processing of the required steps And audio data receiving step of receiving placed al, characterized in that it comprises a reproduction step of reproducing the audio data received by the processing of the audio data receiving step.

In the voice recording apparatus and the voice recording method of the present invention, voice data is divided, a keyword is extracted from the divided voice data, and a tag is added to the divided voice data based on the extracted keyword. The tag list and voice data that have been added are transmitted to the voice reproduction device.

In the audio reproducing apparatus and the audio reproducing method of the present invention, the tag list transmitted from the audio recording apparatus is received, the received tag list is displayed in chronological order, and the displayed tag is displayed. From the list, the specified tag was selected, the audio recording device was requested to transmit the audio data corresponding to the time position of the selected tag, and the requested audio data was received from the audio recording device and received. The audio data is played.

In the audio recording / reproducing system and the audio recording / reproducing method of the present invention, the audio recording device divides the audio data, extracts the keyword from the divided audio data, and divides the audio data based on the extracted keyword. A tag is added to the generated audio data, the tag list and the audio data are transmitted to the audio reproducing device, the audio reproducing device receives the list of tags transmitted from the audio recording device, and the received tag list. Are displayed in chronological order, a predetermined tag is selected from the displayed list of tags, and the audio recording device is requested to transmit audio data corresponding to the time position of the selected tag. The voice data is received from the voice recording device, and the received voice data is reproduced.

[0018]

BEST MODE FOR CARRYING OUT THE INVENTION A configuration example of a voice recording / reproducing system when the present invention is applied to a system for recording / reproducing a telephone call will be described below with reference to FIG.

This voice recording / reproducing system includes a voice recording device 1 that receives orders and complaints from customers via a telephone circuit, and a voice connected to the voice recording device 1 via a network 31 including a telephone circuit and the Internet. It is composed of a playback device 21. The voice recording device 1 is
Configured as a server, the audio playback device 21 is configured as one of a plurality of clients connected to it.

The control unit 3 of the voice recording device 1 controls each unit in response to a user's instruction input from the operation unit 2.
The voice input unit 4 inputs a voice, supplies the input voice to the voice storage unit 5, and stores the voice. The division processing unit 6 reads the voice data from the voice storage unit 5, divides the voice data into a group of utterances, outputs the divided voice data to the voice recognition unit 9, and outputs the voice data of all the voice data. The data storage unit 1 calculates a temporal position and stores information (hereinafter, referred to as recording time) regarding the calculated temporal position.
Output to 0.

Used by a user to describe a word (for example, "lamp", "display", etc.) used to describe a situation, a proper noun such as a model name of a product, or a customer's situation or desire. A keyword such as a word to be input is input from the keyword input unit 7 based on a user operation, supplied to the keyword storage unit 8, and stored. This keyword is independently prepared for each person who wants to provide the service by the voice recording device 1 (the owner of the voice reproducing device 21). At this time, the importance of the keyword is also input from the operation unit 2. The importance is, for example, “high”,
The information is ranked in several stages, such as "medium" and "low". The keyword storage unit 8 calculates the priority from the keyword input from the keyword input unit 7, adds the priority to the keyword and stores it, and supplies it to the voice recognition unit 9 as appropriate.

The voice recognition unit 9 refers to the keyword supplied from the keyword storage unit 8 and searches the voice data supplied from the division processing unit 6 for the same keyword. When the searched voice data includes the same keyword as the keyword stored in the keyword storage unit 8, information indicating that the searched keyword is located at the recording position (hereinafter, this information will be referred to as “keyword”). (Referred to as a tag) and the importance of the keyword are added. When the keyword is not included, the audio data is output to the data storage unit 10 and stored without adding the tag.

The data storage unit 10 associates the voice data, the tag data, and the priority supplied from the voice recognition unit 9 with the recording time input from the division processing unit 6, and stores the data separately for each speaker. To do. Further, the data storage unit 10 is controlled by the output data control unit 12, reads out these data, and supplies them to the data transmission unit 13.

The data storage unit 10 stores data in a format that allows only a list of tag data arranged in time series to be read from the stored data.

The request information receiving unit 11 includes the network 31.
When the request transmitted from the request information transmitting unit 24 of the audio reproducing device 21 is received via the, the output data control unit 1
Output to 2. The output data control unit 12 to which the request is input from the request information reception unit 11 controls the data storage unit 10 to output the requested data to the data transmission unit 13. The data transmission unit 13 transmits these data supplied from the data storage unit 10 to the data reception unit 25 of the audio reproduction device 21 via the network 31.

The control unit 23 of the audio reproducing device 21 prepared by the applicant who desires to provide the service by the audio recording device 1.
Controls each unit in response to a user's instruction input from the operation unit 22. The request information transmitting unit 24 transmits a signal requesting required data to the request information receiving unit 11 of the voice recording device 1 via the network 31. The data receiving unit 25 receives the data transmitted from the data transmitting unit 13 of the voice recording device 1, supplies the data to the data storage unit 26, and stores the data. The data storage unit 26 is the data receiving unit 2
The data supplied from No. 5 is stored, and the tag data among them is output to the tag display unit 27 as an index, the list of data is output to the data search unit 28, and the designated voice data is output to the voice output unit. To 29.

The tag display unit 27 uses the tag data supplied from the data storage unit 26 as an index, in chronological order.
The tags are displayed in different colors according to their priority, and when the user selects a tag on the display unit 27, the selected information is output to the data search unit 28. The data search unit 28 is supplied with the data list stored in the data storage unit 26 from the data storage unit 26, and the supplied list includes the audio data in the reproduction range selected by the user. If it is determined that the voice data is insufficient, the request information transmitting unit 24 outputs information indicating the insufficient portion.
When it is determined that there is no shortage in the audio data, the information indicating that there is no shortage is output to the data storage unit 26.

The request information transmitting section 24 includes a data searching section 28.
Thus, when the information indicating the lacking part of the data is input, a signal requesting the lacking part is transmitted via the network 31.
It is transmitted to the request information receiving unit 11 of the voice recording device 1. The voice output unit 29 outputs the voice data supplied from the data storage unit 26 as voice.

Next, a voice recording process in the voice recording device 1 of FIG. 1 will be described with reference to the flowchart of FIG.

In step S1, the receptionist of the voice recording device 1 receives a call from the customer of the owner of the voice reproducing device 21. For example, if there is a call as shown in FIG. 3 between the customer and the receptionist, the voice input unit 4 inputs the voice and supplies the input voice data to the voice storage unit 5 for storage.

In step S2, the division processing section 6
From the voice data stored in the voice storage unit 5, a block of speech is divided and read out, and this voice data is supplied to the voice recognition unit 9 in the subsequent stage.

In step S3, the division processing section 6
The recording time of the divided audio data read out is calculated, and the calculated recording time is output to the data storage unit 10.

In step S4, the voice recognition section 9
It is searched whether the voice data supplied from the division processing unit 6 includes a keyword. Details of the processing will be described later with reference to the flowchart in FIG.

In step S5, the voice recognition unit 9
It is determined whether or not a keyword is detected in the voice data. If a keyword is detected, the process proceeds to step S6, and the keyword (tag) and the importance of the keyword (stored in the keyword storage unit 8) are voiced. It is added to the data and output to the data storage unit 10. Data storage unit 10
Saves the data input from the voice recognition unit 9 for each speaker based on the recording time.

When it is determined in step S5 that no keyword is detected, the process proceeds to step S7,
The data storage unit 10 distinguishes and stores the voice data for each speaker based on the recording time.

FIG. 4 schematically shows a state in which the call contents of FIG. 3 are tagged in this way and stored in the data storage unit 10. That is, "ZZ-1234
is. Is it 8? "ZZ-123 in the call content of"
Since "4" was registered as the keyword, it is added as a tag to the voice data of the call content. Similarly, in the same manner, "Lamp" is added to the voice data of the call content "Not attached. The lamp next to XX is ..." and "Model" is added to the voice data of the call content "Model ...". "Display" is associated with the voice data of the call content of "..." and "Not relevant. △ Option is associated with the voice data of the call content of" ... "as tags.

After the processing of steps S6 and S7, in step S8, the voice recognition unit 9 determines whether or not there is subsequent data, and if there is, it returns to step S2 and repeats the above-mentioned processing to continue data. If it is determined that there is not, the voice recording process ends.

Incidentally, in the above-mentioned voice recording processing example,
When the voice data is divided in step S2, it is divided in units of a unit of utterance. It is possible to

Details of the keyword search process in step S4 of FIG. 2 will be described below with reference to the flowchart of FIG. In the example shown below, the priority of the keywords is, in order of the keyword related to the product number, the keyword related to the technical term, and the keyword related to the general term,
Although set to "high", "medium", and "low", the keyword and its priority are arbitrarily set by the user.

In step S21, the voice recognition unit 9
Judges whether or not the voice data supplied from the division processing unit 6 includes a keyword related to the product number. If the voice data includes a keyword related to the product number, the process proceeds to step S22, and the voice data The product number as a tag and the priority “high” are added to the, and output to the data storage unit 10. If the voice data does not include the product number, the process proceeds to step S23.

In step S23, the voice recognition unit 9
Judges whether or not the audio data supplied from the division processing unit 6 includes a keyword related to a technical term, and if the audio data includes a keyword related to a technical term, the process proceeds to step S24, and the audio data To the data storage unit 10 with the technical term as a tag and the priority “medium” added thereto. If the voice data does not include the technical term, the process proceeds to step S25.

In step S25, the voice recognition unit 9
Judges whether or not the voice data supplied from the division processing unit 6 includes a keyword related to a general term, and if the voice data includes a keyword related to a general term, the process proceeds to step S26 and the voice data Is added to the general term as a tag and the priority “low”, and output to the data storage unit 10.

If it is determined in step S25 that the voice data does not include a general term, or if the processes of steps S22, S24, and S26 are completed,
The process ends.

Through the above processing, for example, as shown in FIG. 6, the voice data is added with the tag and the priority information, and is output to the data storage unit 10 based on the recording time.
Saved.

The owner of the audio reproducing device 21 accesses the audio recording device 1 via the network 31 at any timing to reproduce the stored audio data.

Next, the audio reproducing process in this case in the audio reproducing apparatus 1 of FIG. 1 will be described with reference to the flowchart of FIG. In step S41, when the user operates the operation unit 22 of the audio reproduction device 21 and inputs a predetermined command, the control unit 23 controls the request information transmission unit 24 in response to the command and via the network 31. The request information receiving unit 11 of the audio recording device 1 is caused to transmit a signal requesting the transmission of the tag data list.

In response to this transmission, the voice recording device 1
Sends audio data (step S in FIG. 9 described later)
73, S75). Therefore, in step S42, the data receiving unit 25 of the audio reproducing device 21 causes the audio recording device 1 to operate.
The tag data transmitted by the data transmission unit 13 is received and stored in the data storage unit 26.

In step S43, the tag display unit 27
Reads out the tag data stored in the data storage unit 26, displays the tag data by color according to the priority of the tag in time series using the tag as an index and for each speaker as shown in the example of FIG. . The user looks at this tag, estimates the position of the call content at the point he or she wants to hear, and selects and specifies the tag by operating the operation unit 22. FIG. 8 shows a state where the "lamp" tag is clicked. When the user looks at the tag and determines that the point he / she wants to hear is not recorded, he / she instructs to refer to another call.

Therefore, in step S44, when the tag on the tag display unit 27 is clicked by the user, the command is taken in, and the operation unit 22 is operated by the user to instruct another call. When
The command is input.

In step S45, the data storage unit 2
6 determines whether the input instruction information from the user is a reference for another call, and if it is a reference for that call, the process proceeds to step S46 to erase the stored data, The process returns to step S41 and the subsequent processing is repeated. That is, a signal for requesting tag data different from the one that is being referred to is transmitted from the request information transmitting unit 24 to the request information receiving unit 11 of the voice recording device 1 via the network 31, and the above-described procedure is performed. Repeated. If the user's instruction is to reproduce the tag in the displayed index, the process proceeds to step S47.

In step S47, the data search unit 2
Reference numeral 8 refers to the list of data stored in the data storage unit 26 and determines whether or not the audio data corresponding to the reproduction range designated by the user is stored in the data storage unit 26.

In step S48, the data search unit 2
When determining that there is no shortage in the audio data corresponding to the reproduction range, 8 outputs information indicating that there is no shortage in the data to the data storage unit 26, and proceeds to step S51. When the data search unit 28 determines that the audio data is insufficient, the process proceeds to step S49.

In step S49, the data search unit 2
Reference numeral 8 denotes the request information transmitting unit 2 which provides information indicating the lack of data.
Output to 4. In response to this, the request information transmission unit 24 sends a signal requesting the lacking portion via the network 31.
It is transmitted to the request information receiving unit 11 of the voice recording device 1. Upon receiving the requested data from the data transmitting unit 13 of the audio recording device 1, the data receiving unit 25 supplies the requested data to the data storage unit 26.

In step S50, the data storage unit 2
6 stores the data supplied from the data receiving unit 25 in chronological order together with the already stored data.

In step S51, the data storage unit 2
6 reads the audio data in the range instructed to be reproduced by the user in chronological order.

In step S52, the data storage unit 2
The data read from 6 is supplied to the audio output unit 29, and is output as audio from the audio output unit 29.

In step S53, the tag display unit 2
7 or the operation unit 22 receives the reproduction instruction from the user, the process returns to step S45, and the above-described processing is repeated. If the instruction input from the user is not received, the audio reproduction processing ends. It

As described above, the data transmitted from the audio recording device 1 to the audio reproducing device 21 is stored in the data storage unit 26.
Temporarily stored in. Therefore, when playing
If even a part of the data within the reproduction range is stored in the data storage unit 26, the data received from the voice recording device 1 need only be insufficient, so that the communication data amount can be suppressed to be small and efficient reproduction can be performed. You can

In step S44, the operation unit 2
By the predetermined operation of 2, for example, it is possible to repeatedly reproduce only the same portion, or to expand and reproduce the range before and after the designated tag.

In step S52, the operation unit 2
The reproduction can be interrupted by the predetermined operation of 2. For example, after that, it is possible to return to step S44 and reproduce another portion.

Next, the data transmission processing executed by the audio recording device 1 corresponding to the above-described reproduction processing will be described with reference to the flowchart of FIG.

In step S71, the voice recording device 1
The request information receiving unit 11 receives the request information transmitted in the process of step S41 from the request information transmitting unit 24 of the audio reproducing device 21, and supplies it to the output data control unit 12.

In step S72, the output data control unit 12 determines that the request supplied from the request information receiving unit 11 is
Determine if the request is for an index. If the request is for an index, the process proceeds to step S73, and the output data control unit 1
2 reads the requested recording time of the index, the keyword, and the priority from the data storage unit 10, and the data transmission unit 1
3 to output. The data transmitting unit 13 transmits this data to the data receiving unit 25 of the audio reproducing device 21. Then, it waits until a new request is transmitted from the audio reproduction device 21. When a new request is transmitted from the audio reproduction device 21, the process returns to step S71 and the above-described processing is repeated.

In step S72, when the output data control unit 12 determines that the received request is not the index-related request, the process proceeds to step S74.

In step S74, the output data control unit 12 determines that the request supplied from the request information receiving unit 11 is
It is determined whether or not the data is audio data. If the request is a request for audio data, the process proceeds to step S75, the output data control unit 12 reads out the requested audio data from the data storage unit 10, and the data transmission unit 13
To output. The data transmitting unit 13 transmits this data to the data receiving unit 25 of the audio reproducing device 21 via the network 31. Then, it waits until a new request is transmitted from the audio reproduction device 21. When a new request is transmitted from the audio reproduction device 21, the process returns to step S71 and the above-described processing is repeated.

If the output data control unit 12 determines in step S74 that the request is not a request for audio data, the process proceeds to step S76.

In step S76, the output data control unit 12 discards this request and waits until a new request is transmitted from the audio reproduction device 21. When a new request is transmitted from the audio reproduction device 21, the process returns to step S71 and the above-described processing is repeated.

When reproducing the voice, the voice recording device 1 performs the data transmission process as described above.

In the above-described configuration example of the present invention, the audio recording device 1 and the audio reproducing device 21 are independent from each other.
Although it is configured as one device, the present invention is, of course, applied to the case where these devices are integrated. A configuration example in that case is shown in FIG. However, parts corresponding to the configuration examples of the audio recording device 1 and the audio reproducing device 21 described above are denoted by the same reference numerals, and description thereof will be appropriately omitted.

In the configuration example of the audio recording / reproducing apparatus 41 of FIG. 10, there is input / output of data between the data storage unit 10 and the tag display unit 27, and the output from the data storage unit 10 is directly voice output. Is supplied to the unit 29. The request information receiving unit 11 and the output data control unit 1 that were present in the configuration of FIG.
2, data transmission unit 13, request information transmission unit 24, data reception unit 25, data storage unit 26, and data search unit 28
Is omitted.

The other structure is the same as that shown in FIG.

The audio recording process in the audio recording / reproducing device 41 of FIG. 10 is the same as the audio recording process in the audio recording device 1 of FIG.

Next, the audio reproduction processing in the audio recording / reproducing apparatus 41 of FIG. 10 will be described with reference to the flowchart of FIG.

In step S91, when the user operates the operation unit 2 of the audio recording / reproducing apparatus 41 and inputs a predetermined command, the control unit 3 controls the data storage unit 10 to display the tag data in the tag display unit 27. To supply. Tag display section 2
The tag data 7 supplied from the data storage unit 10 is used as an index to display the tag data in different colors according to importance in chronological order to prompt the user to make a selection.

In step S92, the tag display unit 27
When the user clicks the tag, the tag is input, and when the user instructs the reference of another call, the operation unit 2 inputs it.

In step S93, it is determined whether or not the instruction input by the user is a reference for another call, and Y
In the case of ES, the process returns to step S91, and the data storage unit 10
From the above, tag data different from the one referred to now is supplied to the tag display unit 27, and the above-described procedure is repeated. If the instruction from the user is not a reference for another call (if it is reproduction of the tag in the displayed index), the process proceeds to step S94.

In step S94, the data storage unit 1
0 reads the audio data corresponding to the reproduction range based on the information indicating the reproduction range designated by the user, which is input from the tag display unit 27, and outputs the audio data to the audio output unit 29.

In step S95, the voice output unit 29
Outputs the voice data supplied from the data storage unit as voice.

In step S96, the tag display unit 2
7 or the operation unit 2 is determined whether or not a reproduction instruction is input from the user, and in the case of YES, Step S93
Returning to, the above-mentioned processing is repeated, and when the input of the instruction from the user is not received, the voice reproduction processing is ended.

The audio reproduction process in the audio recording / reproducing device 41 is performed as described above.

The configuration example of the voice recording / reproducing apparatus 41 is applied to, for example, an answering machine. In this case, it is possible to quickly grasp only the main points without playing back the messages recorded on the answering machine one by one in real time.

In the present invention, the tag display method may selectively display only those having a high degree of importance, or display them based on various criteria, such as arranging the appearance frequencies of keywords as criteria. It is possible.

Further, in the above-described embodiment, the tag index is displayed on the tag display section 27. However, for example, an operation section for receiving an input from the user on the same screen displaying the tag. 2 or information related to the displayed tag can be displayed.

[0084]

As described above, according to the voice recording apparatus and method of the present invention, the tag is added to the voice data, and the tag list and the voice data are transmitted to the voice reproducing apparatus. It becomes possible to retrieve the necessary information more quickly when the playback device plays back.

According to the audio reproducing apparatus and method of the present invention, the list of tags transmitted from the audio recording apparatus is displayed in chronological order, and a predetermined tag is selected from the displayed tag list. Since the audio data corresponding to the time position of the selected tag is received from the audio recording device and the received audio data is reproduced, it is possible to retrieve the necessary information more quickly.

Further, according to the audio recording / reproducing system and method of the present invention, the audio recording device extracts a keyword from the input audio data, adds a tag to the audio data based on the extracted keyword, And the audio data is transmitted to the audio reproducing device, and the audio reproducing device displays the list of tags transmitted from the audio recording device in chronological order and selects from the displayed list of tags. Since the audio data corresponding to the time position of the tag is received from the audio recording device and reproduced, the necessary information can be retrieved more quickly.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an audio recording / reproducing system to which the present invention is applied.

FIG. 2 is a flowchart illustrating a voice recording process of the voice recording device in FIG.

FIG. 3 is a diagram showing an example of a sound recorded in step S1 of FIG.

FIG. 4 is a diagram showing an example of audio data recorded by adding a tag.

5 is a flowchart illustrating a process of searching for a keyword in step S4 of FIG.

6 is a diagram showing an example of data storage in the data storage unit of FIG.

FIG. 7 is a flowchart illustrating an audio reproduction process of the audio reproduction device in FIG.

8 is a diagram showing a display example of tags in step S23 of FIG.

9 is a flowchart illustrating a data transmission process of the audio recording device of FIG.

FIG. 10 is a block diagram showing a configuration of an audio recording / reproducing device to which the present invention is applied.

11 is a flowchart illustrating an audio reproduction process of the audio recording / reproducing device in FIG.

[Explanation of symbols]

1 Audio recorder 2 operation part 3 control unit 4 Voice input section 5 Voice memory 6 division processing unit 7 Keyword input section 8 keyword storage 9 Speech recognition unit 10 Data storage 11 Request information receiver 12 Output data control unit 13 Data transmitter 21 Audio playback device 22 Operation part 23 Control unit 24 Request information transmitter 25 Data receiver 26 Data storage 27 Tag display 28 Data Search Department 29 Audio output section 31 network 41 Audio recording / reproducing device

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G06F 17/30 380 G06F 17/30 380Z 3/16 340 3/16 340A G10L 13/00 G10L 3/00 551A 15/00 531W 15/08 R 15/10 N 19/00 F Term (reference) 5B075 ND14 NK02 NK21 NK31 NR03 NR05 PP13 PQ02 PQ04 PQ05 PQ22 PQ46 PQ75 PR08 5D015 AA04 KK02 5D045 DB01

Claims (10)

[Claims] 1. A dividing unit that divides voice data, a keyword extracting unit that extracts a keyword from the voice data divided by the dividing unit, and the keyword extracting unit extracts the keyword based on the keyword extracted by the keyword extracting unit. An audio recording device comprising: an adding unit for adding a tag to the audio data divided by the dividing unit; a list of the tags; and a transmitting unit for transmitting the audio data to an audio reproducing device. 2. A voice input unit for inputting a voice, a voice storage unit for storing the voice data input by the voice input unit, and a time position storage unit for storing the time position of the voice data divided by the dividing unit. Further comprising: a keyword storage unit that stores the keyword; and a reception unit that receives a request from the audio reproduction device, wherein the dividing unit divides the audio data stored by the audio storage unit, The keyword extraction means extracts the keyword stored by the keyword storage means, and the transmission means transmits the list of tags and the audio data in response to a request from the audio reproduction device. The voice recording device according to claim 1, wherein the voice recording device is a recording medium. 3. The voice recording device according to claim 1, further comprising a storage unit that stores the tags by distinguishing them according to the priority of the keyword. 4. The voice recording device according to claim 3, wherein the storage unit organizes and stores the tags based on a time series. 5. A dividing step of dividing voice data, a keyword extracting step of extracting the keyword from the voice data divided by the processing of the dividing step, and a keyword extracted by the processing of the keyword extracting step. Based on the above, the audio data including an adding step of adding a tag to the audio data divided by the processing of the dividing step, a list of the tags, and a transmitting step of transmitting the audio data to an audio reproducing device. Recording method. 6. A list receiving means for receiving a list of tags transmitted from an audio recording device, a display means for displaying the list of tags received by the list receiving means in chronological order, and the display means. From the list of tags displayed,
Selecting means for selecting a predetermined tag, requesting means for requesting the audio recording device to transmit audio data corresponding to the time position of the tag selected by the selecting means, and requesting by the requesting means An audio reproducing apparatus comprising: an audio data receiving unit that receives the audio data from the audio recording device; and a reproducing unit that reproduces the audio data received by the audio data receiving unit. 7. The display unit distinguishes and displays the tags according to a difference in priority.
The audio reproduction device according to. 8. A list receiving step of receiving a list of tags transmitted from a voice recording device, a display step of displaying the list of tags received by the processing of the list receiving step in chronological order, the display. From the list of the tags displayed by the processing of step, a selection step for selecting a predetermined tag, and transmission of audio data corresponding to the time position of the tag selected by the processing of the selection step, A request step of requesting an audio recording device; an audio data receiving step of receiving the audio data requested by the processing of the request step from the audio recording device; and a reproduction of the audio data received by the processing of the audio data receiving step. And a reproducing step for reproducing the sound. 9. A voice recording / reproducing system comprising a voice recording device for recording a voice of a speaker and a voice reproducing device for reproducing voice data recorded by the voice recording device, wherein the voice recording device comprises: Keyword extraction means for extracting a keyword from the voice data divided by the division means, and addition for adding a tag to the voice data divided by the division means based on the keyword extracted by the keyword extraction means Means, a list of the tags, and a transmitting means for transmitting audio data to the audio reproducing device, wherein the audio reproducing device receives a list receiving means for receiving the tag list transmitted from the audio recording device, Display means for displaying the list of tags received by the list receiving means in chronological order, From the list of the tags displayed by serial display means,
Selecting means for selecting a predetermined tag, requesting means for requesting the audio recording device to transmit audio data corresponding to the time position of the tag selected by the selecting means, and requesting by the requesting means An audio recording / reproducing system comprising: audio data receiving means for receiving the audio data from the audio recording device; and reproducing means for reproducing the audio data received by the audio data receiving means. 10. A voice recording device for recording a voice of a speaker,
And an audio recording / reproducing method of an audio recording / reproducing system configured by an audio reproducing device for reproducing the audio data recorded by the audio recording device, wherein the audio recording method of the audio recording device is a division for dividing the audio data. A keyword extracting step of extracting a keyword from the voice data divided by the processing of the dividing step; and a keyword dividing step of the dividing step based on the keyword extracted by the processing of the keyword extracting step. An adding step of adding a tag to the audio data; a list of the tags; and a step of transmitting the audio data to the audio reproducing device, wherein the audio reproducing method of the audio reproducing device is transmitted from the audio recording device. A list receiving step of receiving the list of said tags, A display step of displaying a list of the tags received by the processing of the list reception step in chronological order, and a selection step for selecting a predetermined tag from the list of the tags displayed by the processing of the display step. And a request step for requesting the audio recording device to transmit audio data corresponding to the time position of the tag selected by the processing of the selection step, and the audio data requested by the processing of the request step An audio recording / reproducing method comprising: an audio data receiving step of receiving from a recording device; and a reproducing step of reproducing the audio data received by the processing of the audio data receiving step.