JP4769345B2 - Audio processing apparatus and recording medium - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a speech processing apparatus and a recording medium, and more particularly, a speech processing apparatus for performing speaker identification for identifying a speaker based on input speech data of the speaker and a program for causing a computer to execute such processing. The present invention relates to a recording medium on which is recorded.
[0002]
[Prior art]
For example, at a major retailer, when a customer purchases a product, the customer's name, address, telephone number, purchased product name, etc. are registered in the customer list, and each customer is referred to by referring to that list. Information that seems to match the needs of the user (for example, information by direct mail) may be provided.
[0003]
[Problems to be solved by the invention]
However, in such a conventional method, there is a problem that registration in the customer list is limited only to customers who have purchased the product. For example, there is a problem in that there is a product to be purchased and information regarding customers who have visited the store many times to determine the product cannot be registered.
[0004]
Also, especially at large retail stores, the number of salesclerks is large, so there are many cases where different salesclerks correspond each time a customer visits. Therefore, it is necessary to repeat the content previously explained to another store clerk, or the explanation received from another store clerk may be repeated again, which is troublesome.
[0005]
The present invention has been made in view of these points, and an object of the present invention is to provide an audio processing device that can refer to information related to past behaviors of customers and users currently supported. .
[0006]
  In the present invention, in order to solve the above problems,Voice data input accepting means for accepting input of speaker's voice data, feature quantity extracting means for extracting feature quantities from the voice data accepted by the voice data input accepting means, and feature quantities extracted by the feature quantity extracting means Or a recording means for supplying the original audio data to the recording apparatus for recording, and a feature quantity obtained by processing the other audio data already recorded in the recording apparatus by the feature quantity extraction means Or another feature quantity already recorded in the recording device and a similarity calculation means for calculating the similarity of a new feature quantity extracted by the feature quantity extraction means, and complementing the speaker identification Attribute information input accepting means for accepting input of attribute information to be performed, and the voice data or feature amount having a similarity higher than a predetermined value calculated by the similarity calculating means An output that causes the display device to display identification information for identifying the audio data in descending order of the similarity value calculated by the similarity calculation unit, and an association unit that associates the attribute information with each other And the recording means supplies the attribute information received by the attribute information input receiving means to the recording device in association with the audio data or feature quantity, and records the attribute information. When calculating the similarity, a feature amount other than the feature amount in which the attribute information associated by the association unit is associated with the attribute information associated with the feature amount that has already been calculated. The similarity is calculated, and the output means displays the attribute information associated with the audio data together with the identification information for identifying the audio data on the display device. Audio processing apparatus is provided to symptoms.
[0009]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a principle diagram for explaining the principle of the present invention.
[0010]
In this figure, audio data input accepting means 1 accepts audio data that is input via, for example, a microphone and is converted into a digital signal by an A / D converter.
[0011]
The feature amount extraction unit 2 extracts a feature amount from the voice data input from the voice data input reception unit 1.
The attribute information input accepting unit 3 accepts input of attribute information related to the speaker corresponding to the speech data input from the speech data input accepting unit 1.
[0012]
The recording unit 4 records the feature quantity extracted by the feature quantity extraction unit 2 and the attribute information input from the attribute information input receiving unit 3 in the recording device 5 in association with each other.
The recording device 5 records the feature amount of the voice data extracted by the feature amount extraction unit 2 and the attribute information of the speaker corresponding to the voice data in association with each other, and in other words, forms a voice database. ing.
[0013]
The similarity calculation unit 6 calculates the similarity between the feature amount of the newly input audio data and the feature amount of the audio data already recorded in the recording device 5.
The associating means 7 associates the newly input audio data with the one having a high degree of association.
[0014]
The output unit 8 refers to the processing result of the similarity calculation unit 6 and displays the attribute information of the feature amount of the voice data having high similarity to the newly input voice data on the display device 9 in a list format, for example. To do.
[0015]
The display device 9 displays the information supplied from the output unit 8 on the screen.
Next, the operation of the principle diagram shown in FIG. 1 will be described. In the following, description will be made on the assumption that, for example, information on customers who have visited a department store is managed by the apparatus shown in FIG.
[0016]
Suppose that a customer visits the store and utters "I want frameless glasses made of XX." Then, the audio data corresponding to the audio is input by the audio data input receiving unit 1 and supplied to the feature amount extracting unit 2.
[0017]
The feature quantity extraction unit 2 extracts a feature quantity from the supplied audio data. Note that information relating to the physical characteristics of the audio data (for example, information relating to the audio formant distribution) is used as the feature amount.
[0018]
The recording unit 4 assigns a predetermined file name to the extracted feature amount, and supplies it to the recording device 5 for recording.
The similarity calculation means 6 calculates the similarity between the feature quantity extracted by the feature quantity extraction means 2 and the feature quantity already recorded in the recording device. If there is a feature quantity whose similarity exceeds a predetermined value, identification information (for example, a file name) for identifying the feature quantity and an attribute recorded in association with the feature quantity Information and the calculated similarity are supplied to the output means 8.
[0019]
The output unit 8 supplies the identification information, attribute information, and similarity supplied from the similarity calculation unit 6 to the display device 9. The display device 9 displays the identification information, the attribute information, and the similarity supplied from the output unit 8 in a list format.
[0020]
Then, when the response to the customer is completed, the store clerk inputs attribute information (information regarding age, sex, purchased product, etc.) from the attribute information input receiving means 3.
[0021]
The recording unit 4 records the feature quantity extracted by the feature quantity extraction unit 2 and the attribute information input from the attribute information input receiving unit 3 in the recording device 5 in association with each other. As a result, new data is added to the database of the recording device 5.
[0022]
The associating means 7 associates (links) the feature amount of the voice data whose similarity with the newly input voice data exceeds a predetermined value with the newly input feature amount. As a result, each item of the database recorded in the recording device 5 is associated with each other according to the similarity (data whose similarity exceeds a predetermined value is linked to each other). In the case where there are a plurality of pieces of data having a high degree of similarity, when one of the linked data is specified, the other data is acquired by following the link.
[0023]
According to the voice processing apparatus related to the present invention as described above, when voice data of a visitor (voice by free utterance) is input, voice having a high similarity is recorded from the database recorded in the recording device 5. The attribute data of the data is acquired and displayed on the display device 9. Therefore, for customers who have visited the store more than once in the past and who have had a conversation with the store clerk, the attribute information is acquired and displayed, so the store clerk refers to the attribute information. , Business negotiations can be promoted more smoothly.
[0024]
FIG. 2 is a block diagram showing an example of the overall configuration of the speech processing system including the embodiment of the present invention.
In this figure, microphones 10a to 10z convert customer voices into electrical signals and supply them to the terminal devices 11a to 11z, respectively.
[0025]
The terminal devices 11a to 11z are, for example, portable terminal devices, convert audio signals input from the microphones 10a to 10z into digital signals, transmit the digital signals to the audio processing device 14, and transmit from the audio processing device 14. The attribute information thus displayed is displayed on the display devices 12a to 12z. It is also possible to input customer attribute information by operating an input unit (not shown).
[0026]
When the customer purchases a product, the register 13 transmits the product name of the product to the sound processing device 14.
The voice processing device 14 has the configuration shown in FIG. 3, and details thereof will be described later.
[0027]
The database 15 records the feature amount obtained as a result of processing the voice data input from the terminal devices 11a to 11z by the voice processing device 14 and the attribute information in association with each other.
[0028]
Note that the terminal devices 11a to 11z, the register 13, the voice processing device 14, and the database 15 form a LAN (Local Area Network) and can exchange information with each other.
[0029]
The router 16 connects a LAN composed of the terminal devices 11 a to 11 z, the register 13, the sound processing device 14, and the database 15 to the Internet 17, for example, with a LAN of another store connected to the Internet 17. It is possible to exchange information between them.
[0030]
Next, the detailed configuration of the audio processing device 14 shown in FIG. 2 will be described with reference to FIG.
The CPU 14a controls each part of the apparatus and executes various arithmetic processes. The LAN unit 14b exchanges data with other devices based on, for example, CSMA / CD (Carrier Sense Multiple Access with Collision Detection).
[0031]
The CD-ROM drive 14c reads necessary data from the CD-ROM.
The hard disk device 14d records a program executed by the CPU 14a.
[0032]
The CRT monitor 14e displays and outputs the processing result of the CPU 14a on the screen.
The memory 14f includes a RAM and a ROM, and reads out or temporarily stores a program required when the CPU 14a performs arithmetic processing.
[0033]
The input device 14g is configured by, for example, a keyboard and a mouse, and is operated when inputting necessary information.
The correspondence between the principle diagram of FIG. 1 and the embodiment of FIGS. 2 and 3 is shown below.
[0034]
That is, the voice data input receiving unit 1 corresponds to the LAN unit 14b. The feature quantity extraction unit 2 corresponds to the CPU 14a. The attribute information input receiving means 3 corresponds to the LAN unit 14b.
[0035]
The recording unit 4 corresponds to the CPU 14a and the LAN unit 14b. The recording device 5 corresponds to the hard disk device 14d or the database 15.
[0036]
The similarity calculation means 6 corresponds to the CPU 14a. The associating means 7 corresponds to the CPU 14a.
The output unit 8 corresponds to the LAN unit 14b. The display device 9 corresponds to the display devices 12a to 12z.
[0037]
Next, the operation of the above embodiment will be described with reference to the flowchart shown in FIG. When this flowchart is started, the following processing is executed. Note that the following processing will be described assuming that audio data is input from the terminal device 11a.
[S1] When an input unit (not shown) of the terminal device 11a is operated, input of audio data starts.
[0038]
Now, a customer visits the store, a conversation with the store clerk is started, and the voice input process is started by the store clerk operating a predetermined key of the input unit of the terminal device 11a. As a result, the audio signal output from the microphone 10a is supplied to the terminal device 11a, where it is converted into a digital signal and then supplied to the audio processing device 14.
[0039]
Note that only when a customer is speaking, a predetermined key may be continuously pressed to prevent both the store clerk and the customer's voice from being input.
[S2] The CPU 14a of the voice processing device 14 extracts feature amounts from voice data input via the LAN unit 14b.
[0040]
As the feature amount, for example, a predetermined phoneme (“A”, “I”, “U”, etc.) is extracted from the speech included in the speaker's speech, and the formant distribution of the extracted phoneme is used. You can do it.
[S3] The CPU 14a reads the feature value of the voice data registered in the database 15 via the LAN unit 14b (the feature value of the voice of the customer who visited the store before).
[0041]
An example of the structure of data registered in the database 15 is shown in FIG. The data shown in this figure is composed of a header d1, a feature quantity d2, and attribute information d3. The header d1 is composed of a file name d11 and a recording date and time d12, as shown in an enlarged manner in the drawing. The attribute information d3 is composed of the customer's gender d31, (estimated) age d32, purchased product d33, planned purchase product d34, and other d35.
[0042]
FIG. 6 is a diagram showing a specific example of the header d1 and the attribute information d3 shown in FIG. As shown in this figure, the file name d11 is given a numerical value generated by incrementing by one each time new data is input, for example.
[0043]
The recording date and time d12 indicates the date and time when the data was registered. The sex d31 and the age d32 are input by the store clerk operating an input unit (not shown) of the terminal device.
[0044]
For example, the purchased product d33 is input from the register 13 when the purchase amount is settled.
The planned purchase product d34 is obtained by inputting information estimated by the store clerk during the dialogue with the customer from an input unit (not shown) of the terminal device.
[0045]
Furthermore, other d35 is obtained by inputting, for example, an impression that the store clerk has held to the customer from an input unit (not shown) of the terminal device.
[S4] The CPU 14a calculates the similarity between the feature amount of the audio data read from the database 15 via the LAN unit 14b and the feature amount extracted in step S2.
[0046]
As a method for calculating the similarity, for example, a correlation between formants of each extracted phoneme may be calculated.
[S5] The CPU 14a determines whether or not there is still an unprocessed feature amount in the database 15. If there is still an unprocessed feature amount, the CPU 14a returns to step S3, and otherwise proceeds to step S6.
[0047]
By repeating the processing of step S3 to step S5, all feature quantities registered in the database 15 are read into the speech processing device 14, and the similarity between the feature quantity and the feature quantity extracted in step S2 is determined. Will be calculated.
[0048]
It should be noted that all of these feature quantities may be stored in the hard disk device 14d.
[S6] The CPU 14a determines whether or not there is a feature quantity with a similarity greater than or equal to a predetermined value among the read feature quantities. If there is at least one, the process proceeds to step S7. If so, the process proceeds to step S8.
[0049]
For example, if there is data having a similarity of 70% or more, the process proceeds to step S7.
[S7] The CPU 14a reads out the attribute information of the feature quantity whose similarity is a predetermined value or more from the database via the LAN unit 14b, and supplies the similarity of each data to the predetermined terminal device 11a as the reliability. To do. As a result, the terminal device causes the display device to display a list of the supplied attribute information and reliability.
[0050]
FIG. 7 shows an example of information displayed on the display device 12a of the terminal device 11a. In this example, the attribute information presumed to belong to the customer who the store clerk is dealing with and its reliability are listed in descending order of reliability. For example, as the candidate No. 1, data of the file name “0204” is displayed, and this customer comes to “1998/11 / 20-11: 24: 34” and the age is “20s”. He is a “male”, plans to purchase a “computer” and is shown to be “interested in graphics”. It is also shown that the reliability of the determination that the customer having this attribute is a customer who is currently visiting the store is “98%”.
[S8] The CPU 14a registers in the database 15 that the customer who visited the store is a new customer.
[S9] The CPU 14a sends a predetermined control code to the terminal device via the LAN unit 14b, and indicates to the display device that the customer visiting the store is a new customer.
[0051]
In the present example, for example, the message “I think you are a new customer” is displayed on the display device 12a of the terminal device 11a.
[S10] The CPU 14a inputs the attribute information output from the register 13 or the terminal device.
[S11] The CPU 14a sends the feature amount acquired in the process of step S2 and the attribute information acquired in step S10 to the database 15, and stores them in association with each other.
[0052]
As a result, data as shown in FIG. 6 is recorded.
According to the above embodiment, when there is a visitor, the voice data is acquired and sent to the voice processing device 14 where the feature amount is extracted. Then, the degree of similarity between the extracted feature quantity and the feature quantity recorded in the database 15 (feature quantity corresponding to all customers who have visited the store in the past and talked with the store clerk) is calculated, and a predetermined value is calculated. When there is a feature amount having the above similarity, the attribute information is read out and displayed on the display device of the terminal device together with the reliability.
[0053]
As a result, if there is a feature that is estimated to be for a customer visiting the store, the attribute information will be displayed along with the reliability, so the store clerk can refer to this information by referring to this information. In addition, since the customer can be treated in consideration of the past behavior and preferences of the customer, the business negotiation can be smoothly advanced.
[0054]
In the above embodiment, the attribute information is recorded in the database. For example, only the identification information and the reliability may be displayed without recording the attribute information. Even in this case, it is possible to know how many times the customer has visited the store in the past, so that it can be used as a reference when conducting business negotiations.
[0055]
In addition, data may be exchanged with other stores (or sales floors) via the Internet 17. By adopting such a configuration, for example, it is recognized as a customer at a certain sales floor or store. Since customers can be treated equally at other sales floors, it is possible to provide more detailed services.
[0056]
Furthermore, in the above embodiment, only the feature amount and its attribute information are recorded in the database 15, but for example, as shown in FIG. You may make it add. Such processing is executed by the CPU 14a corresponding to the association means 7 when a new feature amount is registered in the database 15.
[0057]
By adopting such a configuration, among the data recorded in the database 15, those having a high similarity are linked to each other, so that data having a high similarity to the voice of the customer visiting the store is obtained. When there are a plurality of data and one of them hits, other data can be easily obtained by referring to the link of the data.
[0058]
As such link information, information as shown in FIG. 9 can be used.
In this example, the similarity of the feature quantities of the file names “0001”, “0003”, “0005”, “0006” (for example, the similarity based on the file name “0001”) is, for example, 70% or more. is there. In such a case, as shown in FIG. 9, link information that circulates all the feature values may be given. As a result, when one of these hits by the search, all the feature values can be acquired by following this link information. For example, if “0003” is acquired first, the link is “0001”, so the feature quantity of the file name “0001” is acquired. Similarly, “0006” and “0005” are acquired. Will be.
[0059]
According to the above embodiment, since it is not necessary to calculate the degree of similarity between all feature quantities, it is possible to shorten the time until information is displayed on the display device. Can be performed smoothly.
[0060]
Next, a configuration example of the second exemplary embodiment of the present invention will be described with reference to FIG. In this figure, parts corresponding to those in FIG. 2 are denoted by the same reference numerals, and description thereof is omitted.
[0061]
In this embodiment, compared with the case of FIG. 2, the microphones 10a to 10z are replaced with headsets 22a to 22z, and the register 13 is excluded. Further, headsets 22 a to 22 z are connected to the public line 20 via a PBX (Private Branch Exchange) 21. Other configurations are the same as those in FIG.
[0062]
The public line 20 is, for example, a public line such as an analog line or ISDN. The PBX 21 has a function of distributing calls to the headsets 22a to 22z.
The headsets 22a to 22z are constituted by a speaker and a microphone, and can make a call with a user who has made a call via the PBX 21. An audio signal on the speaker side (user's audio signal) is supplied to the terminal devices 11a to 11z.
[0063]
In this embodiment, when a user who has purchased a product (in this example, a personal computer) receives a phone call regarding the product, the user searches for attribute information having a high degree of similarity and feature amount of the voice data of the user and displays the display devices 12a to 12a. 12z is displayed to support the operator's response.
[0064]
The processing executed in the above embodiment is the same as that shown in FIG. 4, and only the data to be handled is different. The operation will be briefly described with reference to FIGS.
[0065]
FIG. 11 is a diagram illustrating an example of the structure of data stored in the database 15 according to the embodiment illustrated in FIG. 10. As shown in this figure, in the embodiment shown in FIG. 10, only the attribute information d4 is different from the case of FIG. That is, the attribute information d4 is composed of the user's gender d41, (estimated) age d42, possessed personal computer type d43, personal computer proficiency d44, consultation content d45, and corresponding d46.
[0066]
FIG. 12 is a diagram showing details of the header d1 and the attribute information d4 shown in FIG. As shown in this figure, the file name is given a value generated by incrementing by 1 each time recording is performed.
[0067]
The recording date and time d12 indicates the date and time when the data was registered. The gender d41 and the age d42 are obtained by inputting the gender and age estimated from the conversation by an operator operating an input unit (not shown) of the terminal device.
[0068]
The personal computer type d43 indicates the type of personal computer owned by the user. The proficiency level d44 indicates the proficiency level of the user with respect to the personal computer, and is indicated by “beginner”, “intermediate”, and “advanced”. Such information is input by the operator by estimating from the content of the conversation.
[0069]
The consultation content d45 is the content of the consultation. Correspondence d46 is a response to the consultation content. These pieces of information are input by operating an input unit (not shown) after the conversation is finished.
[0070]
FIG. 13 is an example of attribute information displayed on the display device on the terminal device side by the process of step S7 shown in FIG.
In this example, three candidates are displayed. The attribute information of candidate No. 1 is KZR-10, which is registered at 10:20:30 on Jan. 20, 1998 and is in his 50s and possesses proficiency level. Information about a man is displayed. It should be noted that the man's previous consultation was that the power could not be turned on, and that the response was that the power cable was not connected. The reliability of the determination that the main person of the telephone is this man is 98%.
[0071]
By referring to such information, the operator can know the type of the personal computer owned by the user who is consulting, the level of proficiency, and the content of the previous consultation. It is possible to provide appropriate information that matches the level of the user.
[0072]
The above processing functions can be realized by a computer. In this case, the processing contents of the functions that the sound processing apparatus should have are described in a program recorded on a computer-readable recording medium, and the above processing is realized by the computer by executing the program by the computer. Is done. Examples of the computer-readable recording medium include a magnetic recording device and a semiconductor memory.
[0073]
When distributing to the market, store the program on a portable recording medium such as a CD-ROM (Compact Disk Read Only Memory) or floppy disk, or store it in a computer storage device connected via a network. In addition, it can be transferred to another computer through the network. When executed by a computer, the program may be stored in a hard disk device or the like in the computer, loaded into the main memory, and executed.
[0074]
【The invention's effect】
As described above, according to the present invention, feature amounts are extracted from speaker's voice data, and the similarity between the extracted feature amount and the feature amount recorded in the recording device is calculated, and the feature amount having a high degree of similarity is calculated. Since the attribute information recorded in association with the similarity is displayed on the display device, an appropriate response to the speaker is taken with reference to the attribute information presumed to be that of the speaker. Can take.
[Brief description of the drawings]
FIG. 1 is a principle diagram for explaining the principle of the present invention.
FIG. 2 is a block diagram showing an example of the overall configuration of a voice processing system including an embodiment of the present invention.
FIG. 3 is a block diagram illustrating a detailed configuration example of the sound processing apparatus illustrated in FIG. 2;
4 is a flowchart for explaining an example of processing executed in the voice processing apparatus shown in FIG. 3;
5 is a diagram showing an example of the structure of data stored in the database shown in FIG. 3. FIG.
6 is a diagram showing an example of a header and attribute information shown in FIG.
7 is an example of information displayed on the display device on the terminal device side as a result of the processing shown in FIG. 4;
8 is a diagram showing an example when link information is added to the data shown in FIG. 6. FIG.
9 is a diagram showing a state of a link based on link information shown in FIG. 8. FIG.
FIG. 10 is a block diagram illustrating a configuration example of a second exemplary embodiment of the present invention.
11 is a diagram illustrating an example of a structure of data stored in the database according to the embodiment illustrated in FIG. 10;
12 is a diagram showing an example of a header and attribute information shown in FIG.
FIG. 13 is an example of information displayed on the display device on the terminal device side as a result of the processing shown in FIG. 4;
[Explanation of symbols]
1 Voice data input acceptance means
2 feature extraction means
3 Attribute information input acceptance means
4 Recording means
5 recording devices
6 Similarity calculation means
7 association means
8 Output means
9 Display device

Claims (4)

Voice data input acceptance means for accepting input of speaker voice data;
Feature quantity extraction means for extracting feature quantities from the voice data received by the voice data input reception means;
A recording means for supplying the characteristic amount extracted by the characteristic amount extracting means or the original audio data to the recording device, and recording it;
The feature amount obtained by processing the other sound data already recorded in the recording device by the feature amount extraction unit, or another feature amount already recorded in the recording device, and the feature amount Similarity calculating means for calculating the similarity of the new feature amount extracted by the extracting means;
Attribute information input receiving means for receiving input of attribute information that complements the speaker identification;
And associating means for associating the attribute information to each other associated with the audio data or the feature value having a similarity above a predetermined value calculated by the similarity calculation means,
Output means for causing the display device to display identification information for identifying the audio data in descending order of the similarity value calculated by the similarity calculation means;
Have
The recording means supplies the attribute information received by the attribute information input receiving means to the recording device in association with the audio data or feature amount, and records the information.
The similarity calculation means, when calculating the similarity, attribute information associated by said association means is associated with the attribute information associated with the feature amount calculated the already to the class similarity score Calculate the similarity with the feature quantity other than the feature quantity,
The output means displays the attribute information associated with the audio data together with the identification information for identifying the audio data on the display device.   The audio processing apparatus according to claim 1, wherein the recording apparatus is connected via a network.   The speech processing apparatus according to claim 1, wherein the attribute information includes at least one of a customer appearance, a customer preference, a purchased product, or a purchase planned product. Computer
Voice data input receiving means for receiving input of speaker's voice data;
Feature quantity extraction means for extracting feature quantities from the voice data received by the voice data input acceptance means;
Recording means for supplying the characteristic amount extracted by the characteristic amount extraction means or the original audio data to the recording device, and recording it.
The feature amount obtained by processing the other sound data already recorded in the recording device by the feature amount extraction unit, or another feature amount already recorded in the recording device, and the feature amount Similarity calculating means for calculating the similarity of the new feature amount extracted by the extracting means;
Attribute information input receiving means for receiving input of attribute information that complements the speaker identification;
Associating means for associating the attribute information with each other, wherein associated with the audio data or the feature value having a similarity above a predetermined value calculated by the similarity calculation means,
Output means for causing the display device to display identification information for identifying the audio data in descending order of the similarity value calculated by the similarity calculation means;
Function as
The recording means supplies the attribute information received by the attribute information input receiving means to the recording device in association with the audio data or feature amount, and records the information.
The similarity calculation means, when calculating the similarity, attribute information associated by said association means is associated with the attribute information associated with the feature amount calculated the already to the class similarity score Calculate the similarity with the feature quantity other than the feature quantity,
The output means displays the attribute information associated with the audio data on the display device together with the identification information for identifying the audio data .
The computer-readable recording medium which recorded the program characterized by the above-mentioned.

Images