JP2000305748A - Voice storage device and method and voice storage system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a voice storage device and method and a voice storage system for automatically performing proper labeling to stored voice information. SOLUTION: When a recording start event is generated, a voice storage program 310 is started so that the storage of voice data 410 obtained by a microphone 4 can be started, and simultaneously a picture image pickup program 350 is started so that one picture data 430 obtained by a camera 6 can be stored. Then, when a recording end event is generated, a labeling program is started, and related data 420 such as an html document for relating the voice data 410 with the picture data 430 is prepared and stored.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice storage device and method, and a voice storage system, for example, a voice storage device and method for storing voice and image in association with each other.
And a voice storage system.

[0002]

2. Description of the Related Art Conventionally, audio storage devices capable of storing audio and video, such as a tape recorder for recording audio, a video recorder for recording video, and a digital recorder for recording both audio and video, have been known. I have.

It is also possible to capture and use such audio information and video information by a computer using a capture board or the like. That is, it is possible to perform operations such as recording, recording, audio reproduction, video reproduction, and still image capture on audio and video data.

[0004] As seen in the WWW (World Wide Web), information can be used in association with information via links.

FIG. 12 is a block diagram showing a configuration of a conventional voice storage system for recording voice data. In the figure, 1 is a computer including a CPU such as a PC or a workstation, 2 is a monitor, 3 is a storage device (hereinafter, memory) for holding programs and data, 4 is a microphone for inputting audio information, Reference numeral 5 denotes a speaker for outputting sound.

In the memory 3, a voice storage program 31 is stored.
0, a voice storage control program 320, a label display program 330, a voice reproduction program 340, voice data 410, related data 420, and the like.

The voice storage program 310 controls the computer 1 to use the sound board or the like to capture voice from the microphone 4 and store the voice data 410 in the memory 3.

[0008] The voice storage control program 320 controls the start and end of voice storage by the voice storage program 310.

The label display program 330 is provided for the monitor 2
Of the related data 420 to the display.

[0010] The sound reproduction program 340 is executed by the computer 1 using a sound board or the like.
Is reproduced on the speaker 5 or the like. The audio reproduction program refers to the related data 420 at the time of audio reproduction.

The voice storage program 310 is realized by storing voice data created by, for example, a general voice capture program. Similarly, the voice storage control program 320 can control the start and end of voice storage by using a general voice capture program or the like.

FIG. 13 shows a voice storage control program 320.
2 shows a flowchart of a voice accumulation process controlled by the CPU. When the voice accumulation control program 320 is started, first, an occurrence of an event such as a key input is waited (S301). Then, when the recording start event occurs in step S302, the voice storage program 310 is activated in step S303. The recorded voice data is stored as voice data 410 in the memory 3 under the control of the voice storage program 310.

If an event of recording end occurs in step S304, the voice storage program 310 ends in step S305, and if an end event occurs in step S306, the voice storage control program 320 ends.

The label display program 330 displays related data 420 such as an html document linked to the audio data 410 as shown in FIG. 14 by using a general web browser or the like. realizable. The sound reproduction program 340 can be realized by using a general sound reproduction program or the like.

As described above, in the conventional voice storage system, these programs are used to refer to the relevant stored voice data based on the relevant data described in an html document or the like. Can be played.

[0016]

Generally, the stored information of voice cannot be confirmed except by hearing. Therefore, in order to search for desired audio data in the above-described conventional audio storage system, it is necessary for the user to actually reproduce a plurality of audio data stored as the audio data 410 and confirm each one.

By pre-performing a so-called labeling operation of associating a word or a file name representing the content of the audio data with a label at the time of storing the audio data, the audio is actually reproduced at the time of the audio data search. Without it, a search by label was possible. However, in this case, the content of the label needs to be registered by the user when the voice data is stored, which is complicated.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and provides a voice storage apparatus and method for automatically labeling stored voice information with an appropriate label, and a voice storage system. With the goal.

[0019]

According to one aspect of the present invention, there is provided a voice storage apparatus having the following configuration.

That is, audio input means for inputting audio information, audio storage means for storing the audio information, auxiliary information input means for inputting auxiliary information corresponding to the audio information, and an auxiliary device for storing the auxiliary information An information storage unit, a label providing unit for adding label information indicating the corresponding additional information to the audio information, and a label storage unit for storing the label information.

For example, the supplementary information is image information.

[0022]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment according to the present invention will be described below in detail with reference to the drawings.

<First Embodiment> FIG. 1 is a block diagram showing a configuration of a voice storage system according to the present embodiment.
In FIG. 1, the same components as those shown in FIG. 12 in the conventional example described above are denoted by the same reference numerals, and detailed description thereof will be omitted.

In the configuration shown in FIG. 1, a camera 6 for inputting image information is provided in addition to the computer 1, monitor 2, memory 3, microphone 4, and speaker 5.

In the memory 3, in addition to the voice storage program 310, the label display program 330, and the voice reproduction program 340, each control program of a new voice storage control program 321, an image pickup program 350, and a labeling program 360 Is stored, and image data 420 is further stored in addition to the audio data 410 and the related data 420.

The image pickup program 350 is started when the sound storage control program 321 starts the sound storage processing (starts the sound storage program 310), and the computer 1 uses the video board or the like to transmit the image data from the camera 6 at that time. A process for taking in one image and storing the image data 430 in the memory 3 is controlled.

The labeling program 360 stores the image data 430 of the camera 6 input at the same time.
Then, related data 420 that associates the sound data 410 with the microphone 4 is created and stored in the memory 3. As the related data 420, for example, ht as shown in FIG.
ml documents are possible.

The voice storage control program 321 starts and ends voice storage by the voice storage program 310,
The image capturing by the image capturing program 350 is controlled.

FIG. 2 shows a flowchart of the sound accumulation process controlled by the sound accumulation control program 321.

When the voice storage control program 321 is started, first, it waits for an event such as a key input (S70).
1).

If an event of starting recording occurs in step S702, the voice storage program 310 is started in step S703. Here, the recording start event occurs when the recording button 7 is clicked on a screen such as that shown in FIG. The recorded voice data is stored as voice data 410 in the memory 3 under the control of the voice storage program 310.

At approximately the same time as the start of recording in step S703, the image capturing program 350 is started in step S704, and one image is captured. The image data captured at this time is stored as image data 430 in the memory 3 under the control of the image capturing program 350.

If the recording end event has occurred in step S705, the voice storage program 310 ends in step S706. Here, the event of the end of recording is generated when the stop button 8 is clicked on a screen such as that shown in FIG.

Almost simultaneously with the end of the recording in step S706, the labeling program 360 is started in step S707, and the voice storage program 310
The related data 420 that associates the audio data 410 stored by the image data 430 with the image data 430 stored by the image capturing program is created and stored in the memory 3. That is, in the present embodiment, the audio data can be stored in association with the image information at the start of the audio storage.

When an end event occurs in step S306, the sound accumulation control program 321 ends.

In the present embodiment, the related data 420 stored in the memory 3 is an html document as shown in FIG. 5 as described above. In the html document, "ima
ge1. “gif” indicates a file name of image data captured by the image capturing program 350. The label display program 330 converts the html document into an image.
e. For example, as shown in FIG. 6, audio data is displayed as a linked image corresponding to the gif file. By clicking this image with a mouse or the like, the corresponding audio data among a plurality of audio data stored as audio data 410 is reproduced.

As described above, according to the present embodiment,
The audio data can be stored in association with the image data. That is, visual labeling can be automatically performed on the stored voice data, so that, for example, voice data search can be easily performed.

In this embodiment, the image data 43
The example in which the storage of 0 (S704) is performed at the start of recording (S703) has been described.
It may be done at the time. In this case, that is, the image data at the end of the recording is stored.

It is also effective to execute image capture at the time when the audio level has risen the most between the start and end of recording, and to store the image data.

Although an example has been described in which a single image data is associated with audio data, a plurality of image data may be captured at the time of recording, and all of them may be associated with the audio data.

<Second Embodiment> Hereinafter, a second embodiment according to the present invention will be described.
An embodiment will be described.

In the above-described first embodiment, an example has been described in which the image pickup is performed simultaneously with the start of the accumulation of the audio data in response to the occurrence of the event of the start of recording. However, the present invention is not limited to this example. . In the second embodiment, by controlling the sound accumulation according to the sound level and by taking an image, the sound data at the time of the change considered to be useful is accumulated and associated with the image data at that time. It is characterized by.

The configuration of the voice storage system according to the second embodiment is almost the same as that of the above-described first embodiment shown in FIG. 1, except that the voice storage control program 321 is changed to the voice storage control program 322 only. The description is omitted.

FIG. 7 shows a flowchart of the sound accumulation processing controlled by the sound accumulation control program 322. In the figure, the same processes as those in FIG. 2 of the first embodiment described above are denoted by the same step numbers, and description thereof is omitted.

In the second embodiment, the recording start / end event monitoring in the first embodiment (S702, S
705) instead of the sound level determination (S801, S80)
2) is performed. That is, step S80
In 1, when the audio level becomes equal to or higher than the predetermined value α, the recording is automatically started. In step S802, when the sound accumulation program 310 is running and the sound level falls below the predetermined value β, the recording is automatically terminated.

Here, the predetermined value may be α = β, but it is preferable that α> β. By doing so, it is possible to accumulate sound for an appropriate period from the point in time when it is considered that some phenomenon such as a high sound level has occurred.

As described above, according to the second embodiment, it is possible to start the accumulation of the sound and the image at the time when the sound level is greatly changed and is considered important. Therefore, it is possible to automatically perform visual labeling on audio data of a period considered to be important and create relevant data, so that appropriate and useful audio information is selected based on the label. Note that, in the second embodiment, an example in which recording is started when the audio level becomes equal to or higher than the predetermined value α has been described. Conversely, when the audio level has become equal to or lower than the predetermined value α, Recording may be started. By doing so, for example, it is possible to capture a change such as a silent state due to an unexpected stop of the device during automatic driving, and to capture an image at the time.

Third Embodiment Hereinafter, a third embodiment according to the present invention will be described.
An embodiment will be described.

In the above-described second embodiment, an example has been described in which the sound accumulation is controlled according to the sound level.
In the third embodiment, the voice storage is controlled based on a change in environment other than the voice, and by capturing an image, the voice data at the time of the change considered to be useful is stored. Is associated with the image data.

FIG. 8 is a block diagram showing the configuration of the voice storage system according to the third embodiment. In the figure,
The same components as those in FIG. 1 described above are denoted by the same reference numerals, and description thereof will be omitted. 8 is characterized in that the environment sensor 7 is further provided, and the voice storage control program 323 is held in the memory 3. The environment sensor 7 may be, for example, a temperature sensor, a vibration sensor, or the like, but may be any sensor that can detect environmental changes other than sound and images.

FIG. 9 shows a flowchart of the sound accumulation process controlled by the sound accumulation control program 323. In the figure, the same processes as those in FIG. 2 of the first embodiment described above are denoted by the same step numbers, and description thereof is omitted.

In the third embodiment, the monitoring of the recording start / end event in the first embodiment (S702, S
705) instead of the sensor signal determination (S901, S90
2) is performed. That is, step S90
In 1, recording is automatically started when a signal from the environment sensor 7 is detected or when the sensor signal becomes equal to or more than a predetermined value α. In step S902, when the sound accumulation program 310 is running and the signal from the environment sensor 7 is no longer detected, or when the sensor signal becomes equal to or less than the predetermined value β, the recording is automatically ended.

As described above, according to the third embodiment, the sound accumulation and the image accumulation can be started at a point in time when some environmental change occurs and is considered important. Therefore, visual data can be automatically labeled with respect to audio data of a period considered to be important, and related data can be created.

<Fourth Embodiment> Hereinafter, a fourth embodiment according to the present invention will be described.
An embodiment will be described.

In the second and third embodiments described above,
Although an example in which audio data is accumulated from the start of audio accumulation has been described, the present invention is not limited to this example. In the fourth embodiment, by capturing audio data and storing audio data from before the start of audio storage, when audio storage is started in response to some environmental change, the sound data before and after that is stored. It is characterized in that audio data can also be provided.

FIG. 10 is a block diagram showing the configuration of the voice storage system according to the fourth embodiment. In the figure, the same components as those in FIG. 1 described above are denoted by the same reference numerals, and description thereof will be omitted. In FIG. 10, the voice storage program 314 and the voice storage control program 32 are stored in the memory 3.
4, and voice capturing data 440.

When the recording start event occurs, the voice storage control program 324 starts the voice storage program 31.
Start 4 Note that the recording start event in the fourth embodiment may be generated by any of the factors described in the second and third embodiments. That is, a recording start event occurs according to a change in the audio level or a change in the environment.

FIG. 11 shows a voice storage control program 324.
9 shows a flowchart of a sound accumulation process by the sound accumulation program 314 started by the program.

When the voice storage program 314 is started, voice capturing is started (S100).
1). The voice capturing data 440 captured here is stored in the memory 3 together with time information at the time of capture. Then, in step S1002, the process waits for an event to occur.

If a recording start event occurs in step S1003, the time at that point is recorded as the recording start time in step S1004.

If an event of recording end occurs in step S1005, the time at that time is recorded as the recording end time (S1006), and then audio data from the appropriate n seconds before the start time to the end time is captured. Extracted from the ring data 440 (S1007),
The voice data 410 is stored in the memory 3 (S100
8).

Then, in step S1009, when an event of the end of the execution of the voice storage program 314 occurs, the voice storage program 314 ends. The execution end event may be generated by any of the factors described in the second and third embodiments.

As described above, according to the fourth embodiment, the sound accumulation can be started a predetermined time before the time when some environmental change such as a change in the sound level occurs. Therefore, audio data of a wider period considered to be important can be accumulated while performing visual labeling.

Incidentally, as the related data 420, step S
The start / end time recorded in step 1004 / S1006 may be included. This makes it possible to provide the time information together with the video at the time of recording.

The recording start / end event occurrence timing in the fourth embodiment is determined by the second and third events described above.
Although the description has been given on the basis of the embodiment, the present invention can be similarly applied to the first embodiment. That is, it is also possible to accumulate the previous audio data based on the manual instruction of the recording start by the user.

<Other Embodiments> The present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a microphone, a speaker, and the like), and can be applied to an apparatus (a single device). For example, VTR
Etc.).

Another object of the present invention is to provide a storage medium storing a program code of software for realizing the functions of the above-described embodiments to a system or an apparatus, and to provide a computer (or CPU) of the system or apparatus.
And MPU) read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium implements the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

As a storage medium for supplying the program code, for example, a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD
-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.

When the computer executes the readout program code, not only the functions of the above-described embodiment are realized, but also the OS (Operating System) running on the computer based on the instruction of the program code. ) May perform some or all of the actual processing, and the processing may realize the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written into a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that the CPU included in the function expansion board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

When the present invention is applied to the storage medium, the storage medium stores program codes corresponding to the flowcharts described above.

[0073]

As described above, according to the present invention, appropriate labeling can be automatically performed on stored audio data.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a voice storage system according to an embodiment of the present invention;

FIG. 2 is a flowchart showing a sound accumulation control process according to the embodiment;

FIG. 3 is a diagram showing an example of occurrence of a recording start event;

FIG. 4 is a diagram showing an example of occurrence of a recording end event;

FIG. 5 is ht as an example of related data in the embodiment.
a diagram showing an ml document,

FIG. 6 is a diagram showing a display example of related data according to the embodiment;

FIG. 7 is a flowchart showing a sound accumulation control process according to the second embodiment;

FIG. 8 is a block diagram showing a configuration of a voice storage system according to a third embodiment;

FIG. 9 is a flowchart illustrating a sound accumulation control process according to the third embodiment;

FIG. 10 is a block diagram showing a configuration of a voice storage system according to a fourth embodiment;

FIG. 11 is a flowchart illustrating a voice accumulation process according to a fourth embodiment;

FIG. 12 is a block diagram showing a configuration of a conventional voice storage system.

FIG. 13 is a flowchart showing a conventional voice accumulation control process;

FIG. 14 is a diagram showing an html document as a related example of related data.

[Explanation of symbols]

 Reference Signs List 1 computer 2 monitor 3 memory 4 microphone 5 speaker 6 camera 310 voice storage program 320 voice storage control program 330 label display program 340 voice reproduction program 350 image capturing program 360 labeling program 410 voice data 420 related data 430 image data

Claims (18)

[Claims] 1. An audio input unit for inputting audio information; an audio storage unit for storing the audio information; an auxiliary information input unit for inputting auxiliary information corresponding to the audio information; An audio storage device comprising: an information storage unit; a label adding unit that adds label information indicating the corresponding additional information to the audio information; and a label storage unit that stores the label information. . 2. The audio storage device according to claim 1, wherein said additional information is image information. 3. The voice storage device according to claim 2, wherein said additional information input means inputs said image information at the time of starting voice storage by said voice storage means. 4. The voice storage device according to claim 1, wherein the label information is represented in an html format. 5. The voice storage device according to claim 1, further comprising display means for displaying the label information. 6. The audio storage device according to claim 1, further comprising audio reproducing means for reproducing the audio information. 7. The voice storage device according to claim 1, further comprising an instruction unit for instructing the voice storage unit to start and end storage. 8. The voice storage means starts voice storage when voice information input to the voice input means is equal to or higher than a first level, and ends voice storage when the voice information is lower than a second level. The voice storage device according to claim 1, wherein: 9. The apparatus further comprises detection means for detecting an environmental change, wherein the voice storage means starts voice storage when the first state is detected by the detection means, and when the second state is detected. The voice storage device according to claim 1, wherein the voice storage is terminated. 10. A voice storage device comprising: a storage unit configured to store voice data input by the voice input unit; wherein the voice storage unit ends the voice storage at a predetermined time before the voice storage start time. The audio storage device according to claim 7, wherein the audio data corresponding to ま で is extracted and stored by the holding unit. 11. The voice storage device according to claim 1, wherein said voice input means is a microphone. 12. The voice storage device according to claim 1, wherein said additional information input means is a camera. 13. An audio storing step of inputting and storing audio information; an auxiliary information storing step of inputting and storing auxiliary information corresponding to the audio information; and the auxiliary information corresponding to the audio information. And a label assigning step of assigning and accumulating label information indicating the following. 14. The method according to claim 1, wherein the additional information storing step is performed substantially simultaneously with the voice storing step.
3. The voice storage method according to 3. 15. The audio storage method according to claim 14, wherein said additional information is image information. 16. An audio input device for inputting audio information, an auxiliary information input device for inputting auxiliary information corresponding to the audio information, a data processing device for processing and storing the audio information and the auxiliary information, Wherein the data processing apparatus creates label information indicating the corresponding additional information for the audio information, and stores the label information together with the audio data and the additional information. A voice storage system characterized by the following. 17. The audio storage system according to claim 16, wherein said additional information is image information. 18. A recording medium on which a program code for voice storage is recorded, wherein the program code includes at least a code for a voice storage step of inputting and storing voice information, and additional information corresponding to the voice information. Recording, wherein a code of an additional information storing step of inputting and storing, and a code of a label providing step of adding and storing label information indicating the corresponding additional information to the audio information are stored. Medium.