JP2001337691A - Voice record unit, speech processing unit, recording medium in which speech processing program is recorded, and voice data processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a voice record unit, a speech processing unit, a recording medium in which a speech processing program is recorded and a voice data processing method, which can choose user information automatically. SOLUTION: The recording medium 17 in which user ID, etc., as well as voice data are recorded by the voice record playback unit can be equipped on the input unit 32 in the computer 30 as the speech recognition unit. When this recording medium 17 is equipped on the input unit 32, the reading and writing are possible by the speech recognition program at the control of CPU 31. The voice recognition program which performs the voice recognition processing and the user information file, etc., are recorded in the recording medium 33, and these are controlled by CPU 31.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an audio recording device, an audio processing device, a recording medium storing an audio processing program, and an audio data processing method, and more particularly, to an audio recording / reproducing device and an audio recognition device. The present invention relates to a speech recognition system that is configured and can recognize user information.

[0002]

2. Description of the Related Art A speech recognition apparatus using an unspecified speaker model is provided with a user information file set for each user or environment in order to improve the recognition rate. For example,
Japanese Patent Application No. 10-255744 discloses a voice recognition system that automatically switches a user information file based on an ID set in voice data in order to eliminate the complexity of switching the user information file. .

[0003]

However, in the above-described speech recognition system, the ID set in the speech data
If the user information file corresponding to the user information file does not exist in the speech recognition device, the user information file using the unspecified speaker model is used, and the user information file having the acoustic model set for each user or environment. Will be lower than in the case where is used.

In order to secure a normal recognition rate, it is conceivable to create a new user information file, or to transfer a user information file created by another voice recognition device. Was also troublesome.

[0005] Accordingly, the present invention has been made in view of the above situation, and has an audio recording apparatus, an audio processing apparatus, a recording medium on which an audio processing program is recorded, and an audio data capable of automatically selecting user information. It is an object to provide a processing method.

[0006]

That is, a first aspect of the present invention is a voice input means capable of inputting voice, a voice data processing means for converting voice input by the voice input means into predetermined voice data, Storage means for converting voice data into text data and storing the text data, wherein the storage means stores voice recognition data used to increase the accuracy of text conversion when converting the voice data into text data. Is stored.

A second invention is a receiving means for receiving voice data in an external voice recording device, a voice recognizing means for converting the received voice data into text, and a technique for converting the text into text when performing the text conversion. Storage means for storing voice recognition data for raising, if the voice recognition data suitable for converting the received voice data to text is not stored in the storage means, And a control unit for controlling the received voice data to be converted to text using voice recognition data stored in the external voice recording device.

According to a third aspect of the present invention, there is provided a receiving means for receiving voice data in an external voice recording device, a voice recognizing means for converting the received voice data to text, Storage means for storing voice recognition data for raising the voice recognition data, the voice recognition data suitable for converting the received voice data to text is stored in the storage means and the external voice recording device. In the case where the stored voice data is stored in both of the above, the control unit performs control so that the received voice data is converted to text using the newer recording date / time or update date / time of the voice recognition data. I do.

In a fourth aspect of the present invention, a computer receives voice data in an external voice recording device, and converts the received voice data into text by using voice recognition data for improving the accuracy of text conversion. In a recording medium on which a voice processing program to be converted is recorded, the voice processing program does not provide a computer with voice recognition data suitable for converting the received voice data into text. In this case, the received voice data is converted to text using voice recognition data stored in the external voice recording device.

According to a fifth aspect of the present invention, a computer receives voice data in an external voice recording device, and converts the received voice data into text using voice recognition data for improving the accuracy of text conversion. In a recording medium on which a voice processing program is recorded, the voice processing program sends to a computer voice recognition data suitable for converting the received voice data into text, a storage device in the computer, and the external voice recording device. In the case where the stored voice data is stored in both, the received voice data is converted to text using the newest recording date / time or update date / time of the voice recognition data.

According to a sixth aspect of the present invention, there is provided a voice data processing method for transferring voice data in a voice recording device to a voice processing device and converting the voice data into text. When the voice recognition data for transferring the transferred voice data to the text processing accuracy is stored in the voice processing device, the voice recognition data in the voice processing device is transferred to the voice processing device. When the transferred voice data is converted to text and the voice recognition data is not stored in the voice processing device, the transferred voice is used by using the voice recognition data in the voice recording device. It is characterized in that data is converted to text.

Further, a seventh invention relates to an audio data processing method for transferring audio data in an audio recording device to an audio processing device and converting the audio data into text. To the above audio processing device,
In the case where voice recognition data for improving the accuracy of converting the transferred voice data to text is stored in both the voice processing device and the voice recording device, the voice recording device uses the newest recording date or time or update date and time. It is characterized in that the transferred voice data is converted into text using voice recognition data.

In the audio recording apparatus according to the first aspect of the present invention, audio is input by the audio input unit, and the audio input by the audio input unit is converted into predetermined audio data by the audio data processing unit. Then, the voice data is converted to a text and stored in the storage unit. The storage unit stores speech recognition data used to increase the accuracy of the text conversion when the text conversion process is performed.

In the voice processing device according to the second aspect of the present invention, the voice data in the external voice recording device is received by the receiving means, and the received voice data is converted into text by the voice recognition means. Further, speech recognition data for improving the accuracy of the text conversion at the time of the text conversion is stored in the storage means. If the voice recognition data suitable for converting the received voice data to text is not stored in the storage unit, the control unit causes the voice recognition data stored in the external voice recording device to be stored. The received voice data is controlled so as to be used to convert the voice data into text.

Further, in the voice processing device according to the third invention, voice data in an external voice recording device is received by the receiving means, and the received voice data is converted into text by the voice recognition means. Further, voice recognition data for improving the accuracy of the text conversion at the time of the text conversion is stored in the storage means. When the voice recognition data suitable for converting the received voice data into text is stored in both the storage unit and the external voice recording device, the control unit records the voice recognition data. Control is performed so that the received voice data is converted to text using the newer date / time or updated date / time.

According to a fourth aspect of the present invention, there is provided a recording medium on which an audio processing program is recorded, in which a computer receives audio data in an external audio recording device, and converts the received audio data into text. In a recording medium recording a voice processing program for converting the received voice data into text using a voice processing program for converting the received voice data into text using a voice recognition data for raising. When the data is not stored in the storage device in the computer, the received voice data is converted to text using the voice recognition data stored in the external voice recording device.

Further, in the recording medium storing the audio processing program according to the fifth invention, the computer is made to receive the audio data in the external audio recording device, and the received audio data is converted into a text. In a recording medium in which a speech processing program for converting into text using speech recognition data for improving accuracy is recorded, the speech processing program instructs a computer to perform speech recognition suitable for converting the received speech data into text. When the data is stored both in the storage device in the computer and in the external voice recording device, the text of the received voice data is written by using the newest recording date / time or date / time of the voice recognition data. Is performed.

According to a sixth aspect of the present invention, in the audio data processing method for transferring audio data in an audio recording device to an audio processing device to convert the audio data into text, If the voice data in the recording device is transferred to the voice processing device, and voice recognition data for improving the accuracy of converting the transferred voice data into text is stored in the voice processing device, Using the speech recognition data in the processing device, the transferred speech data is converted into text. On the other hand, when the voice recognition data is not stored in the voice processing device, the transferred voice data is converted into text using the voice recognition data in the voice recording device.

Further, in the audio data processing method according to the seventh invention, in the audio data processing method for transferring the audio data in the audio recording device to the audio processing device and converting the audio data to text. The voice data in the voice recording device is transferred to the voice processing device, and the voice recognition data for improving the accuracy of converting the transferred voice data into text is stored in both the voice processing device and the voice recording device. When the voice data is stored, the transferred voice data is converted into text using the voice recognition data with the newest recording date or update date.

[0020]

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

FIG. 1 is a diagram showing a schematic configuration of a speech recognition system according to an embodiment of the present invention.

As shown in FIG. 1, the voice recognition system includes a portable recording medium 1, a voice recording / reproducing device 2 capable of recording a user ID, which is data unique to a user, together with voice data, The computer 3 is a voice recognition device that performs voice recognition processing based on voice data recorded on the medium 1. This computer 3
The input device 5 includes a display 6 as a display device, and operation members 7 such as a keyboard and a mouse (pointing device).

Here, the audio recording / reproducing apparatus 2 will be described.

FIG. 2 is a block diagram of a voice recording / reproducing apparatus which is a component of a voice recognition system according to an embodiment of the present invention.

As shown in FIG. 2, in this audio recording / reproducing apparatus, a microphone 11 as an audio input means is
Amplifier (AMP) 12, Low-pass filter (LPF) 1
3. It is connected to a digital signal processing unit (DSP) 15 via an A / D converter 14. The digital signal processing unit 15 is connected to a system control unit (CPU) 16 which controls various controls of the audio recording / reproducing apparatus.

In addition to the digital signal processing unit 15, the system control unit 16 includes a recording medium 17, a display 18, an external memory 19 for recording a user information file, a recording button (REC) 21a, and a reproduction button (REC). PLAY) 21b, a stop button (STOP) 21c, a fast-forward button (FF) 21d, a fast-return button (REW) 21e, and a menu button (MENU) 21f.

The digital signal processing unit 15 includes:
D / A converter 23, low-pass filter (LPF) 2
4. A speaker 26 is connected via an amplifier (AMP) 25.

The A / D converter 14 and the digital signal processing unit 15 constitute audio data processing means for converting an input analog audio signal into predetermined digital audio data.

The system control unit 16 controls the operation of the digital signal processing unit 15 and the recording medium 17 as well as the various units of the audio recording / reproducing apparatus, and responds to the operation of a plurality of buttons on the operation input unit 12. Read out a predetermined user ID,
Control of writing, that is, also serves as a user ID identification unit. Further, the system control unit 16 has an internal memory for recording a user ID therein (not shown).

The recording medium 17 records audio data encoded by the digital signal processing unit 15 under the control of the system control unit 16 and stores the audio data in the same file in which the audio data is recorded. A user ID corresponding to the audio data is recorded. Further, the recording medium 17 is provided with an area for storing a user information file. When the user information file does not exist in the recording medium 17, the user information file is transferred from the external memory 19.

The system control unit 16 compares the update date and time of the user information file in the external memory 19 and the update date of the user information file in the recording medium 17 each time the recording medium 17 is newly mounted on the audio recording / reproducing apparatus. According to the result of this comparison, overwrite updating is performed in accordance with the latest state.

Next, the audio recording operation in the audio recording / reproducing apparatus thus configured will be described.

In the audio recording / reproducing apparatus according to the present embodiment, when audio data is recorded on the recording medium 17, a user ID corresponding to the audio data, that is, ID information unique to the user is stored in the audio data. Is recorded in the same file. Then, the user of the audio reproducing apparatus can arbitrarily register a user ID recorded together with the audio data.

Hereinafter, the setting operation of the user ID registration will be described with reference to the flowchart of FIG.

First, in step S1, the system controller 16 determines whether or not the user has pressed the menu button 21f for a predetermined time T seconds, for example, 3 seconds. If the menu button 21f has not been pressed for a predetermined time T seconds by the user, the process proceeds to step S2, where the system control unit 16 considers that there is a setting intention of the user user ID, and 18 displays an ID setting screen. As a result, the user ID can be set. On the other hand, in step S1, the menu button 21f
Is pressed for a predetermined period of time, the process proceeds to step S7, and after recording a voice described later and creating a file, a process of registering and changing the user ID is performed.

Next, in step S3, it is determined whether or not the user has input a predetermined operation button on the operation input unit 21, for example, a predetermined four-digit ID code. Here, when the ID code is input, the system control unit 1
6 recognizes this code.

In this embodiment, it is assumed that the ID code is composed of a combination of predetermined alphanumeric characters such as Arabic numerals and Roman characters. These four-digit alphanumeric characters are provided by predetermined buttons, for example, a fast-forward button 21d and a fast-return button 21.
It is assumed that the selection is made with e and the playback button 21b is selected.
The button used for this setting is not limited to this, and another button of the operation input unit 21 may be used.

When the user ID is input by the above operation, the process proceeds to step S4, and the system control unit 16 records the user ID in its internal memory (not shown). Thereby, the user ID is registered. Then, the process proceeds to step S6, where the recording mode, the BEE
Various operation settings such as a P sound and time adjustment are performed.

On the other hand, if the user ID is not set in step S3, the flow shifts to step S5 to determine whether a predetermined time has elapsed. If the predetermined time has not elapsed, the process proceeds to step S3, and the setting of the ID is determined again. On the other hand, if the ID is not set within the predetermined time, the user ID is not set, and the menu setting ends.

Next, after the file is created by recording the voice, that is, the voice data and the user ID are stored in the recording medium 17.
The case where the user ID is registered and changed after the user ID is recorded will be described.

First, a file number whose user ID is to be changed is displayed on the display 1 by a predetermined operation at the time of stop, in the case of this embodiment, by the fast forward button 21d and the fast rewind button 21e.
8 is displayed. Then, as described above, the menu button 2
If 1f is pressed for a predetermined time T seconds, the process proceeds to step S7, where user ID registration and change are enabled.

At this time, the system control unit 16
The header part of the audio data recorded on the recording medium 17 is searched, and the user ID of the header of the selected file is searched.
Is detected and displayed on the display 18.

Next, the user I
D is registered or changed. When registration or change is determined, the system control unit 16 rewrites the user ID recorded in the file header.

By the above operation, registration of the user ID,
Changes are made.

Next, a recording process for recording a voice in the voice recording / reproducing apparatus will be described.

When the system control unit 16 detects that the recording button 21a has been pressed, the audio signal input from the microphone 11 is amplified by the amplifier 12. An unnecessary frequency band is cut off from the output of the amplifier 12 in order to prevent the occurrence of aliasing noise in the low-pass filter 13.

Next, in the A / D converter 14,
After the audio signal, which is an analog signal, is converted into a digital signal, it is input to the digital signal processing unit 15. In the digital signal processing section 15, the audio data converted into the digital signal is compression-converted (encoded) into data of a predetermined format. The encoded audio data is sent to the system control unit 16 via a buffer (not shown). Further, the system controller 16 outputs the input audio data to the recording medium 17.

Here, the operation of recording the audio data and the user ID on the recording medium 17 will be described with reference to the flowchart of FIG.

First, in step S11, the system controller 16 determines whether or not the recording mode is set. If the recording is being performed, the process proceeds to step S12 to determine whether the recording, that is, one file is completed. When the recording (file) is completed, the process proceeds to step S13, and the system control unit 16 determines whether the user ID is registered in the internal memory of the system control unit 16.

If it is determined in step S13 that the user ID is registered, the process proceeds to steps S14 and S15, where the user ID is recorded at a predetermined address of the file header of the recording medium 17. . As a result, a user ID is assigned to the recording medium 17 for each file.

On the other hand, if the user ID is not registered in the internal memory of the system control unit 16, the process proceeds to steps S16 and S15, where the default user ID (0000) is recorded by the system control unit 16 in the same manner as described above. It is recorded in the file header of the medium 17.

When recorded on the recording medium 17, the file header of each file includes, for example, a file number, a recording start time, a user ID, as shown in FIG.
Information such as a recording end time and a recording date and time is written at a predetermined address.

If it is determined in step S11 that the mode is not the recording mode, the operation waits for an input of another operation button.

Next, a speech recognition apparatus in a speech recognition system according to an embodiment of the present invention will be described.

FIG. 6 is a block diagram showing the configuration of a speech recognition apparatus which is a component of the speech recognition system according to one embodiment of the present invention.

As shown in FIG. 6, in the present embodiment, a computer 30 is employed as a speech recognition device.

The inside of the computer 30 includes a CPU 31 which is a component of a voice recognition unit which performs voice input processing, display processing, operation control, etc., in addition to voice recognition processing, an input device 32 which is voice input means, and a recording medium. 33, display device 34,
It has an operation unit 35 such as a keyboard and a mouse.

The recording medium 33 is composed of a hard disk or the like, and stores a voice recognition program for performing voice recognition processing as a component of the voice recognition unit, a user information file as user information (user information), and the like. These are controlled by the CPU 31. The user information includes an acoustic model, word correction information, and training information.

The input device 32 can be loaded with the recording medium 17 on which the user ID and the like are recorded together with the audio data by the audio recording / reproducing device. When the recording medium 17 is mounted on the input device 32, reading and writing can be performed under the control of the CPU 31 by the voice recognition program. The CPU 31 has an R (not shown).
An AM is connected, a voice recognition processing program is loaded on the RAM, and various processes are performed.

A user ID is set in each of the user information files. The user ID has the same format as the user ID recorded by the audio recording / reproducing device, and is composed of a combination of predetermined alphanumeric characters such as Arabic numerals and Roman characters. At the time of voice recognition, this user ID
Is selected.

Next, the speech recognition operation of the speech recognition apparatus will be described with reference to the flowchart of FIG.

The recording medium 17 on which the user ID is recorded together with the above-mentioned audio data is taken out from the above-mentioned audio recording / reproducing apparatus and attached to the input device 32 by the user.
Next, the voice recognition processing program is started by the CPU 31 by a predetermined operation.

FIG. 8 is a diagram showing a display example of an operation when the voice recognition processing program used in the present embodiment is started, and shows a voice file compressed and recorded on the recording medium 17. Is a list display.

Then, in step S31, the user operates the operation unit 35 with a mouse, a keyboard, or the like to select a file for executing voice recognition processing, and instructs execution of voice processing. For example, when the operation unit 35 is a keyboard, it is selected by a cursor key and executed by an execution key. Note that this operation may be another key or an operation method limited thereto.

When the voice recognition execution command is recognized by the CPU 31, the process proceeds to step S32, where the CPU 31 searches the recording medium 17 for a file specified by the user to perform the voice recognition process, and Is searched. In the header, as described above, the user I
In addition to D, information such as recording date and time, recording start time, and recording end time is recorded as index information (see FIG. 5).

Next, in step S33, the CPU 31 detects the user ID from the address where the user ID is recorded. Further, in step S34, the detected user ID is the default user ID recorded when the user has not designated the audio recording / reproducing apparatus.
(0000) is checked.

If the detected user ID is not the default user ID, the process proceeds to step S35,
The CPU 31 checks whether or not the user information file corresponding to the detected user ID exists in the recording medium 33.

When the existence of the user information file is confirmed, the flow shifts to step S36, and the existence of the user information file in the recording medium 17 is similarly confirmed.
Here, if the user information file exists, the process proceeds to steps S37 and S38, and the last update date and time of each file are compared.

Next, in step S39, the recording medium 1
7 is transferred to the recording medium 33. Then, the process proceeds to step S40, and the transferred user information file in the recording medium 33 is set as the user information file used for the voice recognition processing.

On the other hand, if there is no user information file on the recording medium 17 in step S36, and if the user information file in the recording medium 33 is the latest file in step S38, It moves to step S41. Then, in this step S41, the user information file in the recording medium 33 is
After the transfer, the process proceeds to step S40, and the user information file in the recording medium 33 is set as the user information file used for the voice recognition processing.

If the same user ID is not detected in step S35, the process proceeds to step S42.
Then, the existence of the user information file in the recording medium 17 is confirmed. Here, when the existence of the user information file in the recording medium 17 is confirmed, the process proceeds to step S43, and the user information file is transferred from the recording medium 17 to the recording medium 33. Thereafter, the process proceeds to step S40, where the user information file in the recording medium 33 is set as the user information file used for the voice recognition processing.

Further, if the user ID is the default ID in step S34, and if the user information file does not exist in the recording medium 17 in step S42, the process proceeds to step S44. Then, a predetermined user information file is used as the user information file used for the voice recognition processing.

In the present embodiment, a user information file having an unspecified speaker model is used as a default in the user information file.

Next, when the CPU 31 confirms that the user information file has been selected, the audio data of the file compressed and expanded by the audio recording and reproducing apparatus is read from the audio compressed file. The compressed audio data is subjected to decompression processing using the same compression algorithm as that recorded by the audio recording / reproducing apparatus by the audio recognition processing program in reverse, and becomes PCM data.

That is, this process is the same as that of the voice recording / reproducing apparatus, and is performed by a computer controlled by the voice recognition processing program.

Next, in the voice recognition device, the PCM data expanded in the above processing is input to the CPU 31. And
In step S45, the voice recognition processing is performed by the CPU 31 according to the voice recognition processing program. Then, in step S46, the result of the recognition is displayed on the display device.

In this embodiment, the voice recognition system using the voice recording / reproducing apparatus using the portable recording medium has been described. However, the present invention is not limited to this. For example, when an audio recording / reproducing device having a built-in recording medium is used, a similar effect can be obtained by directly connecting to a voice recognition system using a predetermined means, for example, an interface represented by USB, optical communication, or the like. It is possible to get.

FIG. 9 is a diagram showing a schematic configuration of a speech recognition system according to another embodiment of the present invention.

As shown in FIG. 9, this voice recognition system is configured by connecting a voice recording / reproducing device 2 and a computer 3 as a voice recognition device by a USB cable 38. The other configuration is the same as that of the above-described embodiment, and the description is omitted.

FIG. 10 is a flowchart for explaining the speech recognition operation in the speech recognition system of FIG.

In the flowchart of FIG. 10, steps S51 to S55, S57, S60 and S64 to S
Step 66 is the same as steps S31 to S35, S37, S40 and S44 to 46 in the above-described flowchart of FIG.

Then, while the voice recording / reproducing apparatus 2 and the computer 3 are connected by the USB cable 38, the voice recognition processing program is started by a predetermined operation.

At step S55, the CPU 31 checks whether a user information file corresponding to the detected user ID exists in the audio recording / reproducing apparatus 2. Then, when the existence of the user information file is confirmed, the process proceeds to step S56, and similarly, the existence of the user information file in the audio recording / reproducing apparatus 2 is confirmed.

If there is a user information file, the flow shifts to steps S57 and S58 to compare the last update date and time of each file. Then
In step S59, the user information file in the audio recording / reproducing device 2 is transferred to the recording medium 33. Thereafter, the process proceeds to step S40, and the transferred file is set as a user information file used for the voice recognition processing.

On the other hand, in step S56, if the user information file does not exist in the audio recording / reproducing apparatus 2, and in step S58, the user information file in the audio recording / reproducing apparatus 2 is the latest file. If there is, the process proceeds to step S61. Then, in this step S61, after the user information file in the recording medium 33 is transferred to the audio recording / reproducing device 2, the process proceeds to step S6.
The process proceeds to 0, and the user information file in the recording medium 33 is set as the user information file used for the voice recognition processing.

If it is determined in step S55 that the same user ID has not been detected, the process proceeds to step S62.
Then, the existence of the user information file in the audio recording / reproducing apparatus 2 is confirmed. Here, when it is confirmed that the user information file exists in the audio recording / reproducing device 2, the process proceeds to step S63, and the user information file is transferred from the audio recording / reproducing device 2 to the recording medium 33. Thereafter, the process proceeds to step S60, and is set as a user information file used for the voice recognition process.

Further, if the user ID is the default ID in step S54, and if no user information file exists in the audio recording / reproducing apparatus 2 in step S62, the process proceeds to step S64. Then, a predetermined user information file is used as the user information file used for the voice recognition processing.

As described above, according to the voice recognition system of the above embodiment, voice data can be voice-recognized without erroneously selecting user information depending on the user or environment. Further, the place and the like are not limited, and the operation at the time of inputting to the speech recognition device can be performed by a person other than the sounding person.

Even when there is no user information file in the voice recognition device, a good recognition result can be obtained by using the user information file in the voice input device.

Further, even when the user ID is not set or the user information file is not created, the voice recognition processing can be performed by the predetermined user information.

According to the above embodiment of the present invention, the following configuration can be obtained.

(1) Voice input means capable of inputting voice, voice data processing means for converting voice input by the voice input means into predetermined voice data, and text processing of the voice data for storage A sound recording device having storage means;
The storage means is used to increase the accuracy of the text data when converting the voice data to text,
A voice recording device, which stores voice recognition data as user information of a user who has recorded the voice data.

(2) Receiving means for receiving voice data in an external voice recording device, voice recognizing means for converting the received voice data into text, and improving the precision of the text conversion at the time of text conversion. Storage means for storing voice recognition data, if the voice recognition data suitable for converting the received voice data to text is not stored in the storage means, A voice processing apparatus comprising: a control unit configured to control to convert the received voice data into text using voice recognition data stored in the voice recording device.

(3) The control means determines the speech recognition data to be used when converting the received speech data into text, based on the user ID of the received speech data. The voice processing device according to (1).

(4) When the voice recognition data suitable for the received voice data is not stored in the external voice recording device, the control means may transmit the predetermined data stored in the storage means. The audio processing device according to the above (2), wherein the received audio data is controlled to be converted into a text by using the audio data.

(5) Receiving means for receiving voice data in an external voice recording device, voice recognition means for converting the received voice data into text, and improving the precision of the text conversion at the time of text conversion. Storage means for storing voice recognition data, wherein the voice recognition data suitable for converting the received voice data to text is stored in both the storage means and the external voice recording device. If it is stored, control means for controlling the received voice data to be converted to text using the newer recording date / time or update date / time of the voice recognition data, and the voice in the voice recording device From the recognition data,
Transmitting means for transmitting the voice recognition data in the voice processing device to the voice recording device when the recording date / time or the update date / time of the voice recognition data in the voice processing device is newer. Audio processing device.

(6) An audio processing program that causes a computer to receive audio data in an external audio recording device and convert the received audio data to text using voice recognition data for improving the accuracy of the conversion to text. In the recording medium on which the voice processing program is stored, the voice recognition data suitable for converting the received voice data into text is transmitted to both the storage device in the computer and the external voice recording device. A storage medium storing a voice processing program, wherein the received voice data is converted into a text using the newest recording date and time or the updated date and time of the voice recognition data.

(7) If the recording date and time or the update date and time of the voice recognition data in the computer is newer than the voice recognition data in the voice recording device, A recording medium storing the audio processing program according to (6), wherein the audio recognition data in the computer is transmitted to the audio recording device.

[0099]

As described above, according to the present invention, there are provided an audio recording apparatus, an audio processing apparatus, a recording medium on which an audio processing program is recorded, and an audio data processing method capable of automatically selecting user information. can do.

[Brief description of the drawings]

FIG. 1 is a diagram showing a schematic configuration of a speech recognition system according to an embodiment of the present invention.

FIG. 2 is a block diagram of a voice recording / reproducing device that is a component of a voice recognition system according to an embodiment of the present invention.

FIG. 3 is a flowchart illustrating a setting operation of user ID registration.

FIG. 4 is a flowchart illustrating an operation of recording audio data and a user ID on a recording medium.

FIG. 5 is a diagram showing an example of a file on a recording medium 17 and a file header for each file.

FIG. 6 is a block diagram illustrating a configuration of a speech recognition device that is a component of a speech recognition system according to an embodiment of the present invention.

FIG. 7 shows a speech recognition operation in the speech recognition device.
This will be described with reference to the flowchart of FIG.

FIG. 8 is a diagram showing a display example of an operation when a voice recognition processing program used in the present embodiment is started, and a list display of voice files compressed and recorded on the recording medium 33; It is.

FIG. 9 is a diagram showing a schematic configuration of a speech recognition system according to another embodiment of the present invention.

FIG. 10 is a flowchart illustrating a voice recognition operation in the voice recognition system of FIG. 9;

[Explanation of symbols]

 1 portable recording medium (recording medium), 2 audio recording / reproducing device, 3 computer, 5 input device, 6 display, 7 operating member, 11 microphone, 12, 25 amplifier (AMP), 13, 24 low-pass filter (LPF), 14 A / D converter, 15 digital signal processing unit (DSP), 16 system control unit (CPU), 17 recording medium, 18 display, 19 external memory, 21 operation input unit, 21a recording button (REC), 21b playback button (PLAY), 21c stop button (STOP), 21d fast-forward button (FF), 21e fast-return button (REW), 21f menu button (MENU), 23 D / A converter, 26 speakers, 30 computer, 31 CPU, 32 inputs Device, 33 recording medium, 34 display device, 35 operation unit.

Claims (7)

[Claims] 1. A voice input means capable of inputting voice, a voice data processing means for converting voice input by the voice input means into predetermined voice data, and a storage means for converting the voice data into text and storing the text data A voice recording device comprising: a voice recording device for storing voice recognition data used to increase the accuracy of text conversion when the voice data is converted to text in the voice recording device. apparatus. 2. A receiving means for receiving voice data in an external voice recorder, a voice recognizing means for converting the received voice data into text, and a voice for improving the precision of the text when converting the text data. Storage means for storing the recognition data; anda voice processing apparatus having the following. If the voice recognition data suitable for converting the received voice data to text is not stored in the storage means, An audio processing apparatus, comprising: a control unit that performs control to convert the received audio data into text using audio recognition data stored in the audio recording apparatus. 3. A receiving means for receiving voice data in an external voice recording device, a voice recognizing means for converting the received voice data into a text, and a voice for improving the precision of the text when converting the text. Storage means for storing recognition data; and voice recognition data suitable for converting the received voice data into text is stored in both the storage means and the external voice recording device. If so, the voice processing apparatus further comprises control means for controlling the received voice data to be converted to text using the newest recording date and time or update date and time of the voice recognition data. . 4. An audio processing program which causes a computer to receive audio data in an external audio recording device and convert the received audio data to text using voice recognition data for improving the accuracy of text conversion. In the recorded recording medium, the voice processing program may provide the computer with the external processing if the voice recognition data suitable for converting the received voice data into text is not stored in the storage device in the computer. A recording medium storing a speech processing program, wherein the received speech data is converted into text using speech recognition data stored in the speech recording device. 5. An audio processing program for causing a computer to receive audio data in an external audio recording device and converting the received audio data to text using voice recognition data for improving the accuracy of text conversion. In the recorded recording medium, the voice processing program sends the voice recognition data suitable for converting the received voice data to text in both the storage device in the computer and the external voice recording device. If stored, a recording medium on which a voice processing program is recorded, wherein the received voice data is converted to text using the newest recording date or time or the updated date and time of the voice recognition data. 6. A voice data processing method for transferring voice data in a voice recording device to a voice processing device and converting the voice data into text data, wherein the voice data in the voice recording device is transmitted to the voice processing device. When voice recognition data for transferring the transferred voice data to improve the accuracy of converting the voice data into text is stored in the voice processing device, the transfer is performed using the voice recognition data in the voice processing device. And converting the transferred voice data to text using the voice recognition data in the voice recording device if the voice recognition data is not stored in the voice processing device. Voice data processing method. 7. A voice data processing method for transferring voice data in a voice recording device to a voice processing device and converting the voice data into text, wherein the voice data in the voice recording device is transmitted to the voice processing device. When the voice recognition data for transferring the transferred voice data and improving the accuracy of converting the voice data into text is stored in both the voice processing device and the voice recording device, the recording date or the update date and time is A voice data processing method, comprising converting the transferred voice data into text using newer voice recognition data.