JP2000285641A - Information recording device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make inputtable the title of a piece of music or the like by a simple work by performing voice recognizing processing to a voice, generating text data corresponding to this voice and recording these text data on a record ing medium corresponding to respective kinds of preceding information. SOLUTION: A voice recognizing part 9 starts operation under the control of a control part 5 and performs voice recognizing processing to an audio signal inputted through a microphone 10. Further, the voice recognizing part 9 converts the result of this voice recognizing processing to text data and outputs them to a bus. Under the control of the control part 5, a hard disk device(HD) 4 records the text data recorded in a title memory 6 when audio data sent out of such a compact disk(CD) part 2 are completely recorded. At such a time, the HD 4 records the text data recorded in this title memory 6 making the text data correspond to every piece of music based on recorded audio data.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to an information recording apparatus, and can be applied to, for example, an audio data recorder using a large-capacity hard disk drive. The present invention makes it possible to input a title or the like by a simple operation by enabling the input of a music title or the like by voice recognition.

[0002]

2. Description of the Related Art Conventionally, audio titles such as a mini-disc device can be used to input a music title, and the input title is used to improve usability.

In such a device, after an audio signal is once recorded, a processing mode is switched to an edit mode, and a title is input by operating a control.

[0004]

However, in the case of inputting a title by operating the operator as described above,
There is a problem that the operation is complicated. In particular, with the increase in the capacity of the recording medium, it is conceivable that many pieces of music are recorded on one recording medium, so that it is required to simplify such a title input operation.

The present invention has been made in view of the above points, and it is an object of the present invention to propose an information recording apparatus capable of inputting a title of a song or the like by a simple operation.

[0006]

According to the first aspect of the present invention, there is provided an information recording apparatus which performs a speech recognition process on a speech and generates text data corresponding to the speech. It is provided with a recognizing means and a recording means for recording the text data on a recording medium in correspondence with each of the above information.

If text data is generated by voice recognition processing and this text data is recorded in association with information, the title of each information can be easily input by voice.

[0008]

Embodiments of the present invention will be described below in detail with reference to the drawings.

(1) First Embodiment (1-1) Configuration of First Embodiment FIG. 2 is a block diagram showing a recorder according to a first embodiment of the present invention. In the recorder 1, the compact disk (CD) unit 2 reproduces the compact disk according to the control command output to the bus BUS,
The audio data that is the result of the reproduction is output. At this time, when the dubbing process is instructed, the compact disc unit 2 reproduces and outputs the audio data at a high transfer speed several tens times the normal reproduction speed.

A digital signal processor (DS)
P) 3 switches the operation in accordance with the control command output to the bus BUS, compresses the audio data output from the compact disk unit 2 to the bus BUS using the memory M during dubbing, and shows the data compression result. Outputs audio data to the bus BUS.

The hard disk drive (HD) 4 has a bus B
The operation is switched according to a control command output to the US, and during dubbing, audio data output from the digital signal processor 3 to the bus BUS is recorded. Thus, the recorder 1 can compress the audio data reproduced at high speed by the compact disk unit 2 by the digital signal processor 3 and then record the data on the hard disk device 4.

Further, while recording the audio data in this manner, the hard disk device 4 sequentially outputs the recorded audio data to the bus BUS in the recording order. At this time, the hard disk device 4 outputs the recorded audio data at a transmission speed corresponding to the standard reproduction speed. The hard disk device 4 is configured to record a plurality of music pieces continuously recorded on the compact disc from the compact disc unit 2, even when the audio data to be transmitted to the bus BUS is in the middle of the music piece, when the recording of one music piece is completed. Then, the audio data to be transmitted to the bus BUS is switched to the audio data of the music to be subsequently recorded.

The hard disk drive 4 further includes a control unit 5
When the recording of the audio data transmitted from the compact disk unit 2 is completed, the text data recorded in the title memory 6 is recorded. At this time, the hard disk device 4 records the text data recorded in the title memory 6 in association with each song based on the recorded audio data. More specifically, audio data of each song and text data corresponding to each song are filed to record these data, and these data are managed by file management for each file.

Here, in this embodiment, the text data is the title of each song and is input by the user by voice. This makes this recorder 1
In this example, the music recorded on the hard disk device 4 is associated with the corresponding text data so that the music can be easily managed, and the music recorded can be managed and identified by the text data.

On the other hand, when a reproduction control command is input from the control unit 5 via the bus BUS, the hard disk device 4 normally converts the audio data recorded based on the file name added to this control command into a reference. Is output to the bus BUS according to the reproduction speed of.

Prior to such reproduction, the hard disk device 4 reads the recorded text data in response to a control command output from the
Output to US. As a result, under the control of the control unit 5, the recorder 1 can list the titles of the recorded tunes as needed and search and confirm the titles.

At the time of reproduction and dubbing, the digital signal processor 7 takes in audio data output from the compact disk unit 2 or the hard disk device 4 to the bus BUS and expands the data. Further, the digital signal processor 7 converts the expanded audio data into an analog signal by an analog / digital conversion circuit (not shown), and then drives the speaker 8. When the digital signal processor 7 drives the speaker 8 using the audio data output from the compact disk unit 2, the digital signal processor 7 stops the data decompression process and directly outputs the speaker 8 based on the audio data output from the compact disk unit 2 to the bus BUS. Drive.

This enables the recorder 1 to listen to audio data reproduced from the compact disc unit 2 or audio data recorded on the hard disk device 4 during reproduction, and to perform high-speed reproduction during dubbing. The song that is dubbed in the can be previewed sequentially and partially.

The voice recognition unit 9 starts operating under the control of the control unit 5 and performs voice recognition processing on a voice signal input via the microphone 10. Here, this speech recognition processing is executed by, for example, an HMM (Hidden Markov Model). Further, the voice recognition unit 9 converts the result of the voice recognition processing into text data and outputs it to the bus BUS. At this time, the speech recognition unit 9
The accuracy of the speech recognition result is determined, and if the accuracy is equal to or less than a predetermined value, a plurality of candidates for the speech recognition result are generated by ambiguous processing, and the plurality of speech recognition results are output as text data.

The display unit 11 is composed of, for example, a liquid crystal display panel, and displays various messages necessary for operating the recorder 1 under the control of the control unit 5. In this series of displays, the display unit 11 displays the title of a song during playback. Prior to reproduction, a title list of songs, a search result of titles, and the like are displayed. On the other hand, during dubbing or the like, a message prompting the user to input the title of the song by voice is displayed by the user's selection.

The control section 5 is constituted by a microcomputer, and controls the operation of the entire recorder 1 by issuing a control command to the bus BUS in response to the operation of the operation element.

FIG. 3 is a flowchart showing a processing procedure in the control unit 5. When the power of the recorder 1 is turned on, the control unit 5 executes an initialization process according to a predetermined processing procedure. Further, when the operation of the playback or recording operation element is detected, the processing procedure shown in FIG. 3 is executed.

That is, the control unit 5 proceeds from step SP1 to step SP2, determines whether or not the user has instructed recording by operating the operation element. If a negative result is obtained here, the control unit 5 proceeds to step SP3. Since the operation of the playback operation is performed, the operation of the operation input that is subsequently input is received, and the corresponding music is reproduced. At this time, the control unit 5 displays text titles recorded on the hard disk device 4 by loading text data recorded on the hard disk device 4 and displaying the text data on the display unit 11 in response to a user operation. Also, the control unit 5
Similarly, the text data recorded on the hard disk drive 4 is searched by the keyword specified by the user,
A list of titles as search results is displayed on the display unit 11. Further, the control unit 5 issues a playback command by designating a music file corresponding to the text data according to the title according to the user's designation in the title list. Thus, the recorder 1 can easily reproduce a song desired by the user by effectively using the text data recorded in association with each song.

On the other hand, if the operator operated by the user is a recording operator, the control unit 5 proceeds to step SP
When a positive result is obtained in step S2, step S
In P5, the compact disk set in the compact disk unit 2 is reproduced at a high speed, and the audio data obtained by the reproduction is compressed by the digital signal processor 3 and recorded on the hard disk device 4.

At this time, the control section 5 records the compact disc set in the compact disc section 2 as it is, according to the user's designation, and also, among the songs recorded on the compact disc, the user desires. The whole operation is controlled so as to selectively record the music.

In parallel with these controls, the control unit 5
In step SP6, a title input process is executed, and the title of each song is input by voice recognition.

At the same time and in parallel with these processes, the control unit 5 expands the audio data recorded on the hard disk device 4 by the digital signal processor 7 and outputs it from the speaker 8 at step SP3.

Thus, the recorder 1 can dub the audio data recorded on the compact disc at a high speed while monitoring the audio data at a standard reproduction speed, and can input a title to each song based on the audio data.

FIG. 1 is a flowchart showing the title input processing in detail. When dubbing music continuously from the compact disc unit 2, the control unit 5 executes this processing procedure for each music. That is, the control unit 5 proceeds from step SP11 to step SP12, where a message is displayed on the display unit 11 and a user's input is accepted as to whether or not to input a title. If the user does not execute any title input operation, the control unit 5
Moves to step SP13, where a title is set by default. Note that, here, when dubbing music continuously from the compact disc unit 2, a number indicating a continuous recording order is assigned to the title according to the default setting. When the title is set in this way, the control unit 5 registers the text data based on the title in the title memory 6, and then proceeds to step SP14 to end the processing procedure.

In response to this, when the user operates a predetermined operation element in response to an inquiry as to whether or not to input a title, the control unit 5 proceeds to step SP15 and displays a dialog prompting the input of a title. Here, as shown in FIG. 4A, in the display of the display unit 11, the control unit 5 forms a compact disk display "CD" indicating a recording source at the upper left corner of the display screen, and On the side, the track number of the compact disc and the time information according to the user's selection are displayed. The time information is any one of the reproduction time or the remaining reproduction time of the entire compact disc, the elapsed recording time of the music being recorded, and the remaining recording time.

Further, the control unit 5 forms a dialog for prompting the input of a title on the display of the track number and the time information, and displays a message for prompting the input of the title in the dialog.

Subsequently, the control unit 5 proceeds to step SP16, activates the voice recognition unit 9, performs voice recognition processing on voice input via the microphone 10, and acquires text data based on the voice recognition result. At this time, the control unit 5
The accuracy based on the speech recognition result is also acquired from the speech recognition unit 9, and in the following step SP17, it is determined whether there are a plurality of candidates based on the speech recognition result based on the accuracy of the speech recognition result.

If the accuracy of the speech recognition result is high, it is considered that the title input by the user is correctly recognized in the speech recognition result, and the control unit 5 proceeds from step SP17 to step SP17.
Move to 18. Here, as shown in FIG. 4B, the control unit 5 forms a dialog on the display unit 11 and displays this speech recognition result.

Here, when the user instructs the registration by operating the operation element, the control unit 5 proceeds to step SP19,
The text data according to the title is stored in the title memory 6.
Register with. Subsequently, the control unit 5 proceeds to step SP20 and, as shown in FIG. 4C, forms a dialog on the display unit 11 and displays a message indicating that the title has been registered. Note that the control unit 5 executes a processing procedure (not shown) in response to a subsequent user operation when the registration is not instructed by the user, and in this case, the voice recognition processing may be incorrect. The input of the name is accepted, and the text data with the correct title name is registered in the title memory 6.

After registering the title of one song in this way, the control unit 5 moves to step SP14 and ends this processing procedure. In response to this, the display unit 11 as shown in FIG. The display of the dialog formed in is ended.

On the other hand, when the accuracy of the speech recognition result is insufficient, the control unit 5 proceeds to step SP22 when a positive result is obtained in step SP17. Here, the control unit 5 displays the titles based on the plurality of text data acquired from the voice recognition unit 9 in a list format on the display unit 11.
To be displayed.

In this case, as shown in FIG. 5, a message prompting the user to input a title name is displayed on the display unit 11 by a dialog (FIG. 5).
(A)), a plurality of title names considered to have been input by the user by voice are displayed (FIG. 5 (B)).

When the plurality of candidates are displayed in this way, the control unit 5 proceeds to step SP22 and accepts a user's selection operation. Here, the selection operation is performed by specifying the number assigned to the display of the title name by voice recognition or operation of the operation element. Control unit 5
When the user selects a title name in this way, the process proceeds to step SP18, where the title name is displayed as shown in FIG. 5 (C). Step S
The process proceeds to P19, where a registration message is displayed in response to the registration instruction by the user, as shown in FIG. 5D, and then the process proceeds from step SP20 to step SP14 to end this processing procedure. Thereby, the control unit 5 also returns the display on the display unit 11 to the original display in this case.

The control unit 5 executes this processing procedure for each song to be recorded on the hard disk device 4 in this way, accepts registration of a title name, and when recording of all songs is completed, the title memory 6 The recorded text data is recorded on the hard disk device 4. At this time, the control unit 5
Records each text data in the hard disk drive 4 so that each title and music correspond.

On the other hand, when reproducing the audio data recorded on the hard disk device 4, the control unit 5
Based on the contents of the corresponding text data, it is determined whether the text data is the default text data. If the tune to be reproduced is a tune having a title recorded according to the default setting, the control unit 5 executes the processing procedure shown in FIG. 1 during the reproduction of the tune, whereby the title of the title is newly selected by the user. The registration is accepted, and the text data with this title name is recorded on the hard disk device 4.

When the mode for changing the title name is selected by the user, the control unit 5 performs the title recognition by voice recognition in the same manner as when inputting the title name by voice for the song whose title name is registered by default. Is received, and the text data with the previous title name is changed by this title name.

(1-2) Operation of First Embodiment In the above configuration, the recorder 1 (FIG. 2)
When the user instructs the reproduction of the compact disk, the reproduction of the compact disk is started from the compact disk unit 2, and the audio data as a result of the reproduction is input to the digital signal processor 7 via the bus BUS. 7
Drives the speaker 8. This makes the recorder 1
Now, you can listen to the compact disc.

On the other hand, when dubbing to the hard disk device 4 is instructed, audio data is reproduced at a high speed from the compact disk unit 2, and the audio data is compressed by the digital signal processor 3. Further, the compressed audio data is recorded on the hard disk device 4. In these processes, in the recorder 1, a compact disc is reproduced at a speed several tens of times the standard reproduction speed, and the reproduced audio data is data-compressed and recorded on the hard disk device 4, whereby, for example, 60 minutes Even with a compact disc on which audio data is recorded, the audio data can be dubbed in several minutes, and the usability can be improved accordingly.

At the time of such dubbing, in the recorder 1, the audio data recorded on the hard disk device 4 is sent to the digital signal processor 7 at a data transfer speed corresponding to a standard reproduction speed. To decompress the data. Further, the speaker 8 is driven by the expanded audio data, so that the music being dubbed can be monitored.

In this process, when a plurality of music pieces are to be dubbed in succession, when recording of one music piece on the hard disk drive 4 is completed, the hard disk drive 4 is monitored so that the music piece being dubbed can be monitored for the following music piece. The audio data to be transmitted is switched, so that when dubbing at a high speed, the touching portion of the music can be confirmed. This makes it possible to input the title name without fail when inputting the title name during recording in this way, and after dubbing at high speed, inputting the title name for one song and then entering The waiting time before inputting the title name can be reduced, and thereby the usability is improved.

In this way, in the recorder 1 (FIGS. 1 and 3), when dubbing in this manner, the user is asked for a title name for each song, and the user is asked to enter a title name. When the input of the title name is not operated, the number according to the recording order is set as the default title name, and this title name is held in the title memory 6 by text data. When the recording is completed, the text data of each song stored in the title memory 6 is recorded on the hard disk device 4.

On the other hand, when the user selects the input of a title name, a guide is displayed via the display of the display unit 11. When a voice is input according to the guide, the voice is subjected to voice recognition processing by the voice recognition unit 9. , Text data indicating the title name is generated. Further, when the user confirms the title based on the text data, the text data is registered in the title memory 6, and when the recording is completed, the text data of each song held in the title memory 6 is recorded on the hard disk device 4. .

Thus, in the recorder 1, a title name can be input by voice input, and a desired title name can be input by a simple operation, thereby improving the usability. In addition, a desired tune can be easily searched and reproduced based on the title input in this manner, thereby improving usability.

In this voice recognition, by prompting the user to input a voice in an interactive manner through the display of the display unit 11, and further by prompting the user to confirm the recognized voice, even a user who is unfamiliar with the operation can definitely do so. A title name can be input, which can also improve usability.

Further, at this time, in this embodiment, when the accuracy of voice recognition is insufficient, a plurality of voice recognition result candidates are displayed, and a corresponding title name is registered according to a user's selection. As a result, in this embodiment, the title name desired by the user can be input without fail, thereby improving the usability.

Further, in this embodiment, the title name can be input by voice while monitoring the touching portion of the song while dubbing at a high speed, thereby completing the dubbing while inputting the title name in a short time. This can also improve usability.

When dubbing of all songs is completed,
By recording the text data by the title name held in the title memory 6 on the hard disk device 4,
The title name can be recorded on the hard disk device 4 by effectively utilizing the idle time of the processing in the recorder 1. Accordingly, the recorder 1 can simplify such complicated control and configuration as in the case where text data is simultaneously recorded on the hard disk device 4 while dubbing, and can record such data by simple processing. .

Thus, in the text data recorded on the hard disk device 4 in this way, the corresponding song itself is stored as one file and associated with the corresponding song by the file management method for each title. And recorded in the hard disk drive 4. As a result, in the hard disk device 4, the audio data recorded in the hard disk device 4 can be easily reproduced by applying various file management methods in the control unit 5 accessing the hard disk device 4, In addition, a corresponding title name can be searched and reproduced, thereby improving usability with a simple configuration.

On the other hand, when reproducing the audio data recorded in this manner, the recorder 1 sends the audio data selected by the user to the bus BUS from the hard disk device 4 at a data transfer speed corresponding to the standard reproduction speed. The audio data is expanded by the digital signal processor 7. Further, the speaker 8 is driven by the expanded audio data, so that a desired music can be previewed.

At this time, prior to playback, the recorder 1 can assist the user in selecting a music piece by using the title name, such as displaying the title name to the user based on the title name recorded on the hard disk device 4. This can also improve usability. During playback, the title of the song currently being played back is displayed, thereby improving the usability.

In reproducing the audio data recorded in the hard disk device 4 in this manner, when reproducing the music in which the title name is recorded by the default setting, the recorder 1 provides the user with the same information as in the case of dubbing. The input of the title name by voice is prompted, and the title name by voice input is recorded on the hard disk device 4 in the same manner as in dubbing.

Thus, in the recorder 1, for example, after dubbing, the title can be input by voice at a new time, thereby improving the usability.

(1-3) Effects of the First Embodiment According to the above configuration, the title of music can be input by voice recognition, so that the title can be input by a simple operation. The usability of the audio device can be improved accordingly.

After the recording of all the songs is completed, the text data held in the title memory is recorded on the hard disk device, so that the usability is improved, and these title names can be input with a simple structure as a whole. Can be.

Further, by managing the music data to be recorded and the text data of the corresponding title name in the file format, it is possible to easily and surely manage these data.

In voice recognition, a message displayed on a display screen prompts a user to input a voice required for voice recognition processing.
The title name can be easily and reliably input, which also improves the usability.

By displaying the title name of the text data recorded in this manner at the time of reproducing the audio data, the user can easily confirm the music being reproduced, thereby improving the usability. Can be.

(2) Second Embodiment The recorder according to the second embodiment has a voice synthesizing unit in addition to the configuration according to the first embodiment, and a voice generated by the voice synthesizing unit. Prompts for the input of a title name in an interactive manner.

That is, in this embodiment, FIG.
Instead of displaying the message of "Please enter title" described above, a message of "Please enter title" is output from the speaker by voice synthesis.

In the confirmation of the title name described with reference to FIG. 4B, the voice synthesizing means is driven by the text data which has been subjected to the voice recognition, whereby, for example, in comparison with FIG. It's okay ".

Instead of displaying the confirmation message of “registered” described above with reference to FIG. 4C, for example, in contrast to FIG. 4C, the message “Register with Mariah Carry” is displayed. Say the message.

In response to these processes, the control unit of the recorder according to the present embodiment accepts confirmation of the result of voice recognition by voice recognition. That is, in the case described above, when a voice recognition result of “OK” is obtained in response to the utterance of the message “Mariah Carry is okay”, the control unit changes the title name based on the voice recognition result to text data. On the hard disk device.

According to the second embodiment, it is possible to promptly input a title name in an interactive manner by voice synthesis and confirm the title name by voice recognition, so that the title name can be input in a so-called hands-free manner. it can. Thus, for example, the present invention can be applied to an in-vehicle device to improve safety and obtain the same effect as in the first embodiment.

(3) Other Embodiments In the above-described embodiment, the case where dubbing is performed at a high speed has been described. However, the present invention is not limited to this. Can be applied.

In the above-described embodiment, the case where audio data is recorded on the hard disk device has been described. However, the present invention is not limited to this. When recording audio data on a recording medium such as an optical disk, and further recording on a memory card. It can be widely applied in cases such as

In the above embodiment, the case where audio data is recorded has been described. However, the present invention is not limited to this, and can be widely applied to the case where a video signal is recorded.

[0072]

As described above, according to the present invention, a title such as music can be input by voice recognition, so that a title or the like can be input by a simple operation.

[Brief description of the drawings]

FIG. 1 is a flowchart showing a processing procedure of a control unit of a recorder according to an embodiment of the present invention.

FIG. 2 is a block diagram illustrating an overall configuration of a recorder according to a control unit in FIG. 1;

FIG. 3 is a flowchart showing a processing procedure of a control unit of the recorder of FIG. 2;

FIG. 4 is a schematic diagram used for describing a processing procedure in FIG. 1;

FIG. 5 is a schematic diagram for explaining a process when the accuracy of a speech recognition result is insufficient.

[Explanation of symbols]

1 ... Recorder, 2 ... Compact disc part, 3,7
... Digital signal processor, 4 ... Hard disk drive, 5 ... Control unit, 6 ... Title memory, 9
... Speech recognition unit, 11 ... Display unit

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification code FI Theme coat ゛ (Reference) G11B 27/00 A 27/10 A

Claims (9)

[Claims] 1. An information recording apparatus for acquiring desired information from a predetermined information source and recording the information on a recording medium, comprising: a voice recognition unit configured to perform voice recognition processing on voice and generate text data corresponding to the voice; Recording means for recording the text data on the recording medium in association with each information. 2. The information recording device according to claim 1, wherein the information recording device sequentially and sequentially records the plurality of pieces of information, the recording unit includes a storage unit for temporarily storing the text data, and after the recording of the information is completed, 2. The information recording apparatus according to claim 1, wherein the text data stored in the storage unit is recorded on the recording medium. 3. The information recording apparatus according to claim 1, wherein the information recording apparatus manages each of the information and the text data in a file format. 4. The information recording apparatus according to claim 1, wherein the voice recognition unit prompts input of voice required for the voice recognition process by a guide using an interactive voice. 5. The information recording apparatus according to claim 1, wherein said voice recognition means prompts input of voice required for said voice recognition processing by displaying a message on a predetermined display screen. 6. The speech recognition unit according to claim 1, wherein the speech recognition unit provides a text data candidate corresponding to the speech to a user, and determines the text data corresponding to the speech based on the selection of the user. Information recording device according to the above. 7. The information processing apparatus according to claim 1, further comprising: reproducing means for reproducing said information from said recording medium; and display means for displaying said text data corresponding to said information reproduced by said reproducing means. 2. The information recording device according to 1. 8. The information recording apparatus according to claim 1, wherein said information is music based on audio data. 9. The information recording apparatus according to claim 1, wherein the information is an image based on video data.