JPH05344223A - User voice recording and reproducing device - Google Patents

Abstract

PURPOSE:To provide a user voice recording and reproducing device capable of shortening the time for user voice recording and listening by an operator. CONSTITUTION:This user voice recording and reproducing device includes a guidance voice storage device 2 storing guidance voice, a guidance reproducing device 3 reading guidance voice, transmitting a guidance to a user 9 and transmitting a reproduction start signal and a guidance reproduction termination signal to a user voice storage device 6, a user voice storage device 6 terminating the storage of user voice when a guidance reproduction termination time is stored and the termination of user voice is detected, and a user voice reproducing device 7 reading user voice, user voice storage start time and guidance reproduction termination time and reproducing the user voice part on and after guidance reproduction termination time.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a user voice recording / reproducing apparatus, and in particular, in the field of operator service, in which the operator accepts orders, inquiries, etc. from the user, and the system listens to the user's requirements. The present invention relates to a user voice recording / reproducing apparatus used for.

[0002]

2. Description of the Related Art Currently, an operator accepts orders, inquiries and the like through direct conversation with a user. Therefore, the labor cost of the operator is the dominant factor in the balance of these acceptance services, and it is desirable for the service provider to reduce the cost. To solve this problem, systematize part of the conversation and
It is possible by shortening the response time per user.

That is, it is possible to replace the operator's standard utterance with machine guidance, temporarily record the user's voice uttered in accordance with the guidance, and then allow the operator to listen to the recorded contents at high speed. Becomes

Conventionally, in the case of realizing such a system, first, after detecting a call from the user, the service provider side sends a guidance to the user to prompt the user to speak necessary information. In response, the user speaks and the system records the user's voice. The recording of the user voice is started at the same time as the reproduction of the guidance, and is ended by detecting the end of the user's utterance or receiving the call disconnection of the user.

Next, when the operator listens to the recorded content of the user's voice, it is assumed that the user utters during the guidance, and is listened from the time when the guidance is reproduced to the end of the user utterance.

Further, in the case of the above method, since a silent time is included between the start of recording the user's utterance and the start of the user's utterance (the beginning portion of the user's voice), a method of deleting the silent portion and reproducing it is also possible. is there. When using this method,
The listening time of the operator is reduced.

[0007]

However, when the operator hears the user voice as it is, it takes the same time as the user's utterance time to hear it.

[0008] On the other hand, even when the silent portion at the beginning of the user voice recording is deleted and reproduced, even if the silent portion is not judged to be silent due to the wraparound of the guidance, the user's utterance during the guidance is heard as it is. There are many. As described above, conventionally, since the effect of shortening the listening time of the user voice by the operator is small, there is a problem that the efficiency of the work cannot be improved by compressing the constraint time of the operator.

The present invention has been made in view of the above points, and an object of the present invention is to provide a user voice recording / reproducing apparatus capable of shortening the time taken by the operator to record and listen to the user voice and the operator's restraint time. To do.

[0010]

FIG. 1 is a block diagram showing the principle of the present invention.

According to the present invention, the guidance for prompting the user 9 to utter the user is reproduced through the voice output device 4, and the user voice from the user 9 corresponding to the guidance is temporarily accumulated through the voice input device 5 and accumulated. In the user voice recording / reproducing apparatus 1 in which the operator 10 reproduces and listens to the user voice via the voice reproducing apparatus 8, the guidance voice accumulating apparatus 2 for accumulating the guidance speech and the guidance speech from the guidance speech accumulating apparatus 2 are read, and the user 9 To the voice output device 4, and when the guidance reproduction is started, a guidance reproduction start signal is output.
A guidance reproducing device 3 that transmits a guidance reproduction end signal to the user voice accumulating device 6 when the guidance is completed.
When the guidance reproduction start signal is received from the guidance reproduction device 3, the user voice accumulation is started and the user voice accumulation start time is accumulated, and when the guidance reproduction end signal is received, the guidance reproduction end time is accumulated and the user voice is terminated. User voice storage device 6 which terminates the storage of the user voice when it detects "," the user voice, the user voice storage start time, and the guidance playback end time are read from the user voice storage device 6, and the operator 10 is notified to the operator 10 via the voice playback device 8. And a user voice reproducing device 7 for reproducing a user voice portion after the guidance reproduction end time.

Further, the user voice reproducing device 7 of the present invention is
The user voice storage portion before the guidance reproduction end time is reproduced at high speed for the operator 10 via the voice reproduction device 8 and the subsequent portion is reproduced at normal speed.

Further, the user voice reproducing device 8 of the present invention is
When the user voice is returned from the high-speed playback state to the normal speed playback, it has a first speed changing means for gently changing the playback speed of the user voice and playing it back.

Further, according to the present invention, the position information of the keyword included in the guidance is stored in the guidance voice storage device 2, and the guidance reproduction device 3 sends the guidance reproduction end signal to the user voice storage device 6 when the guidance reproduction is completed. The user voice accumulating device 6 obtains the keyword position information of the guidance being reproduced from the guidance voice accumulating device 2 and calculates and stores the keyword end time without transmitting, and the user voice reproducing device 7 causes the user voice accumulating device 7 to accumulate the user voice. The keyword end time is read from the device 6 and the accumulated portion of the user voice after the keyword end time is reproduced to the operator 10 via the voice reproduction device 8.

The user voice reproducing device 7 of the present invention is
For the operator 10 via the voice reproduction device 8, the accumulated portion of the user voice before the keyword end time is reproduced at high speed, and the subsequent portion is reproduced at normal speed.

Further, the user voice reproducing apparatus 7 of the present invention is
When the user voice is reproduced at the normal speed from the high speed reproduction state, the second speed changing means is provided which gently changes the reproduction speed of the user voice and reproduces it.

[0017]

According to the present invention, the recorded portion before the guidance reproduction end time is reproduced at high speed, and the subsequent portion is reproduced at the normal speed, so that the operator can listen without uttering meaningless speech or silent portions. In addition, the user voice is reproduced at high speed during the guidance reproduction, particularly during the reproduction of the keyword portion, and the subsequent recording portion is reproduced at the normal speed. This is because most of the utterances of the user during the guidance reproduction are residual words or the like that are unconsciously uttered, and thus the meaningless utterance tendency particularly appears particularly in the keyword portion of the guidance. Therefore, the operator can listen to only the user voice recording portion while ignoring the user voice during the keyword portion reproduction.

[0018]

First, a first embodiment of the present invention will be described.

FIG. 2 is a diagram showing the configuration of the user voice recording / reproducing apparatus of the present invention. In the figure, the same components as those in FIG. 1 are designated by the same reference numerals.

The user voice recording / playback apparatus 1 includes a guidance voice storage apparatus 2 for storing a guidance voice file 21 for storing guidance voice, and a guidance playback apparatus for playing back the guidance stored in the guidance voice storage apparatus 2 through a speaker 15. 3, a user voice storage device 6 having a user voice file 61 for storing the user voice input from the microphone 16, and a user voice reproduction device 7 for processing and reproducing the user voice for the operator 10.

The guidance voice storage device 2 stores the guidance voice file 21 and keyword position information (not shown) on the hard disk. The guidance reproducing device 3 is
A D / A converter (not shown) and a memory (not shown) are used to temporarily store the guidance voice file 21 acquired from the guidance voice storage device 2 in the memory, and
The guidance is output to the speaker 15 via the A converter.

The user voice accumulating device 6 is composed of an A / D converter (not shown) and a memory (not shown), and A / D converts the user voice input via the microphone 16 and then stores it in the memory. Accumulate in.

The user voice reproduction device 7 is composed of a D / A converter (not shown), a memory and a calculation device (not shown), and the user voice file 61 obtained from the user voice storage device 6 is temporarily stored in the memory. The user voice is stored and output to the speaker 17 via the D / A converter.

Next, the operation of the first embodiment of the present invention will be described. FIG. 3 is a flow chart showing the operation of the first embodiment of the present invention.

Step 1: For the user 9, the guidance reproducing device 3 reads the guidance voice file 21 from the guidance voice storage device 2.

Step 2: The guidance reproducing device 3 reads the contents of the guidance voice file 21 and outputs it from the speaker 15 to the user 9.

Step 3: The guidance reproduction device 3 sends a guidance reproduction start signal to the user voice storage device 6 at the same time when the reproduction of step 2 is started.

Step 4: On the other hand, the user voice storage device 6 starts recording the user voice and stores the user voice recording start time.

Step 5: When the reproduction of the guidance is completed, a guidance reproduction end signal is sent to the user voice storage device 6.

Step 6: When the operator 10 listens to the user voice, the user voice reproduction device 7 first reads the user voice file 61 from the user voice storage device 6.

Step 7: Only the user voice accumulated after the guidance end time stored in the user voice accumulating device 6 in step 4 is reproduced.

In the above-mentioned flowchart, the reproduction process of step 7 may be a method of performing high-speed reproduction for the portion before the guidance end time at the time of accumulating the user voice, and reproducing at the normal reproduction speed after the guidance end time. In addition, the reproduction speed is gradually decreased from the high speed state to the normal reproduction speed in principle for reproduction.

Next, a second embodiment of the present invention will be described. FIG. 4 is a flow chart showing the operation of the second embodiment of the present invention.

Step 401: For the user, the guidance reproducing device 3 reads the guidance voice file 21 from the guidance voice storage device 2.

Step 402: Guidance reproducing device 3
Reads out the content of the guidance voice file 21 and outputs it to the user 9 from the speaker 15.

Step 403: Guidance reproducing device 3
Sends a guidance reproduction start signal to the user voice storage device 6 at the same time when the reproduction in step 402 is started.

Step 404: On the other hand, the user voice storage device 6 starts recording the user voice and stores the user voice recording start time.

Step 405: Simultaneously with the guidance reproduction in step 402, the user voice accumulating device 6 acquires the keyword position information of the guidance being reproduced from the guidance voice accumulating device 2 and calculates the keyword reproduction end time,
accumulate.

Step 406: When the operator 10 listens to the user voice, the user voice reproducing device 7 first reads the user voice file 61 from the user voice accumulating device 6 and sets the keyword reproduction end time corresponding to the user voice file 61. read out.

Step 407: User voice reproducing device 7
Of the user voice reproduces only the accumulated portion of the user voice after the keyword end time, and outputs the user voice from the speaker 17 to the operator 10.

In the operation of the user voice reproducing device 7 in step 407, of the user voice accumulated in the user voice file 61, the portion before the keyword end time is reproduced at high speed, and then the portion after the keyword end time is reproduced. There is also a method of playing at normal speed.

FIG. 5 shows an example of the relationship between the system guidance of the present invention and user utterance. In the same figure, (a) shows the system guidance, and the hatched portion is the keyword portion. FIG. 6B shows the user voice. Also,
The portion indicated by d reproduces the user voice at high speed and outputs it to the speaker 17. The portion indicated by e reproduces the user voice at the same speed and outputs it to the speaker 17. Therefore, the voice heard by the operator 11 is reproduced at a high speed in the guidance part and the user voice part is reproduced at a normal speed as shown in (c).

FIG. 6 shows an example of the guidance of the present invention. In the figure, the underlined portion is the keyword portion.

[0044]

As described above, according to the present invention, the content of the user voice file before the end of the guidance is played at high speed, the content of the user voice file after the end of the guidance is played normally, and the keyword portion of the guidance is used. Since the speed of the user voice being reproduced is reproduced for the operator, the listening time of the user's utterance can be shortened.

This makes it possible to reduce the operator restraint time and improve the efficiency of work.

[Brief description of drawings]

FIG. 1 is a principle configuration diagram of the present invention.

FIG. 2 is a configuration diagram of a user voice recording / reproducing apparatus of the present invention.

FIG. 3 is a flowchart of a reproduction process according to the first embodiment of this invention.

FIG. 4 is a flowchart of a reproduction process according to the second embodiment of this invention.

FIG. 5 is a diagram showing an example of the relationship between the system guidance of the present invention and user voice.

FIG. 6 is a diagram showing an example of guidance of the present invention.

[Explanation of symbols]

 1 User voice recording / playback device 2 Guidance voice storage device 3 Guidance playback device 4 Voice output device 5 Voice input device 6 User voice storage device 7 User voice playback device 8 Voice playback device 9 User 10 Operator 15 Speaker 16 Microphone 17 Speaker 21 Guidance voice File 61 User audio file

Claims (6)

[Claims] 1. A guidance for prompting the user to utter a user is reproduced via a voice output device, a user voice from the user corresponding to the guidance is temporarily stored, and the accumulated user voice is reproduced by an operator via the voice reproduction device. In a user voice recording / reproducing apparatus that reproduces and listens to, a guidance voice accumulating device that accumulates guidance voice, reads the guidance voice from the guidance voice accumulating device, and sends the guidance to the user via the voice output device. Then, a guidance reproduction start signal is transmitted when the guidance reproduction is started, and a guidance reproduction end signal is transmitted to the user voice storage device when the guidance is ended, and the guidance reproduction start signal is transmitted from the guidance reproduction device. Upon reception, user voice accumulation starts and user voice accumulation starts. A user voice storage device that stores the product start time, stores the guidance reproduction end time when the guidance reproduction end signal is received, and ends the user voice storage when the end of the user voice is detected; And a user voice reproducing device for reading the user voice, the user voice accumulation start time, and the guidance reproduction end time, and reproducing the user voice portion after the guidance reproduction end time to the operator via the voice reproduction device. User voice recording / playback device characterized by: 2. The user voice reproduction device reproduces a high-speed reproduction portion of the user voice before the guidance reproduction end time to the operator via the voice reproduction device, and reproduces the subsequent portion at a normal speed. The user voice recording / reproducing apparatus according to claim 1, wherein 3. The user voice reproduction device, when returning the user voice from a high speed reproduction state to a normal speed reproduction,
3. The user voice recording / reproducing apparatus according to claim 2, further comprising a first speed changing unit that gently changes the reproduction speed of the user voice to reproduce the user voice. 4. The position information of a keyword included in the guidance is stored in the guidance voice accumulating device, and the guidance reproducing device transmits a guidance reproduction end signal to the user voice accumulating device when reproduction of the guidance is completed. The user voice storage device acquires the keyword position information of the guidance being reproduced from the guidance voice storage device, calculates a keyword end time, and stores the keyword end time. 2. The keyword end time is read out from the storage device, and the user voice storage part after the keyword end time in the user voice file is played back to the operator via the voice playback device. User voice recording and playback device. 5. The user voice reproduction device performs high-speed reproduction for a portion before the keyword end time in the user voice file to the operator via the voice reproduction device, and normal speed reproduction for the subsequent portions. 5. The user voice recording / playback apparatus according to claim 4, wherein the voice recording / playback apparatus is performed. 6. The user voice reproduction device, when reproducing the user voice from a high speed reproduction state at a normal speed, reproduces the user voice by gently changing the reproduction speed.
6. The user voice recording / reproducing apparatus according to claim 5, further comprising speed changing means.