JP2001075776A - Device and method for recording voice - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a voice recording device which makes it possible to adjust the reading-aloud speed at which a speaker reads aloud an object sentence to be recorded by determining the phonation time of the sentence and notifying the speaker of the sentence and information for reading the sentence aloud according to the phonation time. SOLUTION: A spoken and recorded sentence storage part 11 stores sentences as objects of voice recording. A spoken and recorded sentence extraction part 12 extracts the spoken and recorded sentences from the storage part 1, one by one. A phonation time length calculation part 13 determines the length of a phonation time for reading aloud one sentence taken out by the extraction part 12. A phonation speed representation display part 14 gives notice of information or the like that a speaker reads aloud according to the phonation time length of the sentence calculated by the calculation part 13 in a form of an image or voice. Consequently, the phonation speed of the speaker can be controlled at the time of voice recording. Consequently, uniform data free of differences in data size and tone quality are generated with the recorded voice.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice recording apparatus and a voice recording method, and more particularly to a voice recording apparatus and a voice recording method capable of adjusting the speed at which a speaker reads out a sentence to be recorded.

[0002]

2. Description of the Related Art In order to create a speech unit dictionary or the like, as a prerequisite, it is necessary to record voices uttered by humans. In such voice recording, for example, a sentence to be recorded is disclosed to a speaker, and a voice uttered based on the sentence is recorded.

[0003]

However, since the speed at which a sentence is read varies from person to person, when a plurality of speakers read a sentence to be recorded, each speaker speaks based on a unique utterance speed. It will be. For this reason, there is a problem that a difference occurs in the data size and sound quality of each speech unit dictionary for speech synthesis created after each speech recording.

[0004] Further, even for the same speaker, the utterance speed is not constant and fluctuations occur, so that there is also a problem that the sound quality of the segments of the same speech unit dictionary is different.

Accordingly, it is an object of the present invention to provide a voice recording apparatus and a voice recording method capable of adjusting the speed at which a speaker reads out a sentence to be recorded.

[0006]

According to the present invention, there is provided a voice recording apparatus for recording a voice of a speaker reading a predetermined sentence, wherein a means for determining a utterance time of the sentence, And a means for notifying a speaker of information for reading out the sentence in time with the utterance time.

[0007] In the audio recording apparatus of the present invention, the information is:
The total utterance time of the sentence displayed together with the sentence and the utterance time of each predetermined unit in the sentence may be used.

Further, the information may be a mark displayed in accordance with the sentence, which indicates a predetermined unit in the sentence in order based on the utterance time.

Further, according to the present invention, there is provided a voice recording apparatus for recording a voice of a speaker who reads a predetermined sentence, wherein: a means for determining a utterance time of the sentence; Means for displaying or not displaying the sentence in order according to the utterance time.

Further, according to the present invention, there is provided a voice recording apparatus for recording a voice of a speaker reading a predetermined sentence, wherein a means for determining a utterance time of the sentence, displaying the sentence, and Means for changing the color of the sentence in accordance with the utterance time for each predetermined unit in the sentence.

In the voice recording apparatus according to the present invention, a syllable, a pause phrase, or an accent phrase constituting the sentence can be adopted as the unit.

Further, according to the present invention, there is provided a voice recording apparatus for recording a voice of a speaker who reads a predetermined sentence, wherein a means for determining a utterance time of the sentence, and a method of continuously moving the sentence. And means for displaying a fixed mark indicating a portion of the sentence to be uttered.

Further, according to the present invention, there is provided a voice recording device for recording a voice of a speaker reading a predetermined sentence, wherein a means for determining a utterance time of the sentence, displaying the sentence, and Means for producing a voice based on the utterance time;
A voice recording device characterized by comprising:

Further, according to the present invention, there is provided a voice recording method for recording a voice of a speaker reading a predetermined sentence, wherein a step of determining a utterance time of the sentence is provided. Notifying the speaker of the information to be read aloud in accordance with the utterance time, thereby providing a voice recording method.

Further, according to the present invention, there is provided a voice recording method for recording a voice of a speaker who reads a predetermined sentence, wherein a step of determining a utterance time of the sentence, And displaying or not displaying the sentence in order according to the utterance time.

Further, according to the present invention, there is provided a voice recording method for recording a voice of a speaker reading a predetermined sentence, wherein a step of determining a utterance time of the sentence, displaying the sentence, and Changing the color of the sentence according to the utterance time for each predetermined unit in the sentence.

Further, according to the present invention, there is provided a voice recording method for recording a voice of a speaker reading a predetermined sentence, wherein a step of determining a utterance time of the sentence, and a step of continuously moving the sentence. And displaying a fixed mark indicating a portion to be uttered in the sentence.

Further, according to the present invention, there is provided a voice recording method for recording a voice of a speaker reading a predetermined sentence, wherein a step of determining a utterance time of the sentence, displaying the sentence, and Producing a voice based on the utterance time;
Is provided.

According to the present invention, a computer for recording a voice of a speaker who reads a predetermined sentence is provided.
A storage medium is provided that stores a program that functions as a unit that determines a utterance time of the sentence, a unit that notifies the utterer of the sentence and information for reading out the sentence in accordance with the utterance time. .

According to the present invention, in order to record the voice of a speaker who reads a predetermined sentence, a computer is provided.
There is provided a storage medium storing a program for functioning as means for determining the utterance time of the sentence, and means for displaying or hiding the sentence in order for each predetermined unit in the sentence in accordance with the utterance time. .

According to the present invention, in order to record a voice of a speaker who reads a predetermined sentence, a computer is provided.
A storage medium storing a program functioning as means for determining the utterance time of the sentence, means for displaying the sentence, and means for changing the color of the sentence in accordance with the utterance time for each predetermined unit in the sentence Is provided.

22. The storage according to claim 18, wherein the unit is a syllable, a pause phrase, or an accent phrase constituting the sentence. A medium is provided.

According to the present invention, a computer for recording a voice of a speaker who reads a predetermined sentence is provided.
A storage medium storing a program functioning as means for determining the utterance time of the sentence, means for continuously moving and displaying the sentence, and means for displaying a fixed mark indicating a part to be uttered in the sentence Is provided.

According to the present invention, in order to record a voice of a speaker who reads a predetermined sentence, a computer is provided.
There is provided a storage medium storing a program for functioning as a means for determining the utterance time of the sentence and a means for displaying the sentence and emitting a voice based on the utterance time.

[0025]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing the configuration of a characteristic portion of the configuration of a sound recording apparatus according to an embodiment of the present invention.

In FIG. 1, reference numeral 11 denotes an utterance recording sentence storage unit in which a plurality of sentences to be recorded are stored.
Reference numeral 12 denotes an utterance recorded sentence extraction unit, and a generated recorded sentence storage unit 11
Utterance sentences are extracted one by one from the utterance.

Reference numeral 13 denotes an utterance time length calculation unit which determines the utterance time length for reading one sentence extracted from the utterance recorded sentence extraction unit 12.

As the utterance time length, a morphological analysis and a pause generation process are performed on the generated recorded sentence, and a time length suitable for uttering is determined from the time length per mora and the time length per pause. be able to.

Here, the mora refers to a syllable that forms a word, and a long sound, a vocal sound, and a sound-repelling sound are counted as one mora. For example,
“Coffee” is 4 mora and “system kitchen”
Is 8 mora. The morphological analysis is to determine the reading of kanji in a sentence mixed with kanji and kana, and to determine a morpheme that is a unit of characters. With pause generation processing, if you try to utter a long sentence at a stretch without breathing, it will become early or without inflection. Is what you do.

For example, if the utterance recorded sentence is a mixture of kanji and kana characters, such as "Today is fine weather." The appropriate utterance time length cannot be determined. Therefore,
Morphological analysis and pose generation processing are performed on the sentence mixed with kanji and kana.

When the morphological analysis and the pose generation processing are performed,
The reading “Today is a good day” and a pose (O) are generated, and it is determined that the sentence is composed of 10 mora and 2 poses. So 2 per mora
Assuming 00 msec and 300 msec per pose, the overall utterance time length suitable for uttering one sentence is 2.
It can be determined as 6 seconds.

Reference numeral 14 denotes a utterance speed expression display unit, which notifies an image or a voice of information or the like which is read out by the speaker according to the utterance time length of the sentence calculated by the utterance time length calculation unit 13. is there.

The audio recording device including the blocks shown in FIG. 1 can be realized by, for example, the system shown in FIG. In FIG. 2, reference numeral 21 denotes a CPU, which operates according to a program for implementing a procedure described later. 2
Reference numeral 2 denotes a RAM, which provides a storage area necessary for the operation of the program. Reference numeral 23 denotes a ROM, which stores a program for implementing a procedure described later. Numeral 24 denotes a disk device which stores the above program and is stored in a memory when used. Reference numeral 25 denotes a display device, which displays the utterance speed created by the above-mentioned program by image or sound. Reference numeral 26 denotes a bus for connecting the above components.

Next, the operation of each block shown in FIG. 1 will be described with reference to the flowchart shown in FIG. In the present embodiment, it is assumed that voice recording is performed when a voice unit dictionary in voice synthesis is created.

In step S31, the utterance recorded sentence extracting unit 1
2 extracts one sentence from the utterance recorded sentence storage unit 11, and proceeds to step S32.

In step S32, the utterance time length calculation unit 1
3 determines the utterance time length suitable for uttering the one utterance recorded sentence extracted in step S31, and proceeds to step S33.

In step S33, the uttered speaker displays the uttered recorded sentence and its utterance speed in an image. Step S3
In S4, it is determined whether an unrecorded sentence remains in the utterance recorded sentence storage unit 11, and if an unrecorded sentence remains, step S3 is performed.
Returning to step 1, the above processing is repeated, and if there is no unrecorded sentence, the processing ends.

Next, step S32 and step S33
Will be described by taking as an example the case where the utterance recorded sentence is “system kitchen”.

In step S33, the time required to utter this sentence is determined. If it is determined to be 0.25 seconds per mora, the time length suitable for utterance is determined to be 2.0 seconds.

Therefore, the sentence “System Kitchen” to be recorded takes 0.25 seconds per mora, and the whole sentence is 2
Over a second, the speaker will read it aloud.

The result is displayed in step S34, for example, as shown in FIG. In the display example of FIG. 4, as the information to be read aloud according to the utterance recording sentence “system kitchen” and the utterance time length, the time to read the entire sentence (2.0 seconds) and the time to read each character (0 .25 seconds)
And are displayed. The speaker can use the time as a guide to read out the recorded speech.

Hereinafter, other display examples in step S34 will be listed.

In the display example of FIG. 5, the arrow 51 indicates the syllable to be read at present while moving rightward based on the calculated time length.

In the display example of FIG. 6, the syllable to be read at present is indicated while extending rightward based on the time length calculated by the indicator 61.

In the display example of FIG. 7, while the syllabary wave 71 extends rightward based on the calculated time length and points to the syllable to be read at present, in the display example of FIG. The syllables are displayed in order based on the syllable unit based on the length of the syllable, and if the utterance is read in order from the syllable that appears, the utterance is read aloud by the calculated time length. Note that the entire sentence may be displayed first, and then hidden one by one in syllable units.

In the display example of FIG. 9, the utterance recorded sentence is displayed with color, and the color is changed in units of the syllable based on the calculated time length. If the sentences are read in order, the utterance recorded sentences are read out with the calculated time length.

In the display example shown in FIG. 10, based on the calculated time length, the utterance recorded sentence is moved so as to flow like a display on an electronic bulletin board. In FIG. 10, the utterance recorded sentence “Kyoha Iitenki I” is from time t to time t.
As the time progresses to +1, it moves to the left as a whole. If the speaker reads out the characters that pass through the fixed mark 81, the speaker has read out the recorded speech with the calculated time length.

In the present embodiment, the display is adjusted in units of syllables, but may be adjusted in units of pause phrases or accent phrases. For example, in the display example of FIG. 8, since the utterance target is specified in units of syllables, the characters may disappear one by one,
Although it appears, the utterance target can be changed from syllable units to pause phrase units and accent phrase units.

Here, the pause phrase is a group of characters sandwiched by one sentence, and the accent phrase is a group of characters including accents.

For example, when there is a sentence "Nihontaro-san is fine," the pose phrase and the accent phrase are
"Nihon / Taro-san // Genki." (/ Is an accent phrase, ○ is a pause phrase) and one pause phrase per sentence.
Contains two accent phrases. One sentence includes one or more pause phrases, and one pause phrase includes one or more accent phrases.

In the present embodiment, the information for reading out the utterance recorded sentence according to the utterance time length is displayed by an image, but it is not only visual but also the utterance time length as in a headphone or a speaker. May be notified to the speaker by voice, and may be realized in an auditory manner.

As described above, according to the present embodiment, the speaker which is an index of the speed at which the utterance recorded sentence is read out is notified to the utterer by the image or the voice. Can control the speech rate of the person. As a result, uniform data having no difference in data size and sound quality is created by the recorded voice.

The present invention may be applied to a system constituted by a plurality of devices or to an apparatus constituted by a single device. A recording medium storing the software program code for realizing the functions of the above-described embodiments is supplied to a system or an apparatus, and a computer (or CPU or MPU) of the system or the apparatus reads out the program code stored in the recording medium. Needless to say, it can also be achieved by executing.

In this case, the program code itself read from the recording medium implements the functions of the above-described embodiment, and the program code itself implements the functions of the above-described embodiment. The recording medium on which the code is recorded constitutes the present invention.

As a recording medium for supplying the program code, for example, a floppy disk, hard disk, optical disk, CD-ROM, CD-R, magnetic tape, nonvolatile memory card, ROM, etc. 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 or the like running on the computer is actually executed based on the instructions of the program code. It goes without saying that a part or all of the above-described processing is performed, and the functions of the above-described embodiments are realized by the processing.

Further, after the program code read from the recording 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, The CPU provided in the function expansion board or function expansion unit performs part or all of the actual processing,
It goes without saying that a case where the function of the above-described embodiment is realized by the processing is also included.

[0059]

As described above, according to the present invention,
The speed at which the speaker reads out the sentence to be recorded can be adjusted.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a characteristic portion of an audio recording device according to an embodiment of the present invention.

FIG. 2 is a block diagram illustrating a configuration example for implementing a voice recording device according to an embodiment of the present invention.

FIG. 3 is a flowchart showing a processing procedure of audio recording.

FIG. 4 is a diagram showing a display example in a process of step S33 in FIG. 3;

FIG. 5 is a diagram showing a display example in a process of step S33 in FIG. 3;

FIG. 6 is a diagram showing a display example in a process of step S33 in FIG. 3;

FIG. 7 is a diagram showing a display example in a process of step S33 in FIG. 3;

FIG. 8 is a diagram showing a display example in a process of step S33 in FIG. 3;

FIG. 9 is a diagram showing a display example in the process of step S33 in FIG. 3;

FIG. 10 is a diagram showing a display example in the process of step S33 in FIG. 3;

[Explanation of symbols]

 11 utterance recorded sentence storage unit 12 generated recorded sentence extraction unit 13 generation time length calculation unit 14 utterance speed expression display unit 21 CPU 22 RAM 23 ROM 24 disk device 25 display device 26 bus

Claims (24)

[Claims] 1. A voice recording device for recording a voice of a speaker who reads a predetermined sentence, comprising: means for determining a utterance time of the sentence; and adjusting the sentence and the sentence to the utterance time. A voice recording device comprising: information for reading out; and means for notifying a speaker of the information. 2. The voice recording apparatus according to claim 1, wherein the information is a total utterance time of the sentence displayed together with the sentence and a utterance time of each predetermined unit in the sentence. 3. The voice recording according to claim 1, wherein the information is a mark displayed in accordance with the sentence, indicating a predetermined unit in the sentence in order based on the utterance time. apparatus. 4. A voice recording device for recording a voice of a speaker who reads a predetermined sentence, wherein: a means for determining a utterance time of the sentence; Means for displaying or hiding the sentence in turn. 5. A voice recording device for recording a voice of a speaker reading a predetermined sentence, wherein: a means for determining a utterance time of the sentence; displaying the sentence; Means for changing the color of the sentence in accordance with the utterance time for each unit. 6. The audio recording apparatus according to claim 2, wherein the unit is a syllable, a pause phrase, or an accent phrase constituting the sentence. 7. A voice recording device for recording a voice of a speaker reading a predetermined sentence, wherein: a means for determining a utterance time of the sentence; and wherein the sentence is continuously moved and displayed; Means for displaying a fixed mark indicating a part to be uttered in the sentence. 8. A voice recording device for recording a voice of a speaker reading a predetermined sentence, wherein: a means for determining a utterance time of the sentence; displaying the sentence; and based on the utterance time. A sound recording device comprising: means for emitting a sound. 9. A voice recording method for recording a voice of a speaker reading a predetermined sentence, comprising: determining a utterance time of the sentence; and adjusting the sentence and the sentence to the utterance time. Notifying the speaker of the information to be read out, and a voice recording method. 10. The voice recording method according to claim 9, wherein the information is an utterance time of the entire sentence displayed together with the sentence and an utterance time of each predetermined unit in the sentence. 11. The voice recording according to claim 9, wherein the information is a mark displayed in accordance with the sentence, indicating a predetermined unit in the sentence in order based on the utterance time. Method. 12. A voice recording method for recording a voice of a speaker who reads a predetermined sentence, comprising: determining a utterance time of the sentence; and determining a utterance time for each predetermined unit in the sentence. A step of displaying or not displaying the sentence in turn in combination. 13. A voice recording method for recording a voice of a speaker reading a predetermined sentence, comprising: determining a utterance time of the sentence; displaying the sentence; Changing the color of the sentence according to the utterance time for each unit. 14. The syllable constituting the sentence, wherein the unit is:
The voice recording method according to any one of claims 10 to 13, wherein the voice recording method is a pause phrase or an accent phrase. 15. A voice recording method for recording a voice of a speaker reading a predetermined sentence, comprising: determining a utterance time of the sentence; displaying the sentence by continuously moving the sentence; Displaying a fixed mark indicating a part to be uttered in the sentence. 16. A voice recording method for recording a voice of a speaker reading a predetermined sentence, comprising: a step of determining an utterance time of the sentence; displaying the sentence; and based on the utterance time. Producing a voice. 17. A computer for recording a voice of a speaker who reads a predetermined sentence, comprising: a computer for determining a utterance time of the sentence; and information for reading the sentence according to the utterance time. And a storage medium storing a program that functions as means for notifying the speaker. 18. The storage medium according to claim 17, wherein the information is the total utterance time of the sentence displayed together with the sentence and the utterance time of each predetermined unit in the sentence. 19. The information processing apparatus according to claim 17, wherein the information is a mark displayed in accordance with the sentence, indicating a predetermined unit in the sentence in order based on the utterance time.
A storage medium according to claim 1. 20. A computer for recording a voice of a speaker reading a predetermined sentence, comprising: means for determining a utterance time of the sentence; for each predetermined unit in the sentence, a computer is sequentially arranged in accordance with the utterance time. A storage medium storing a program that functions as means for displaying or hiding the sentence. 21. A computer for recording a voice of a speaker reading a predetermined sentence, comprising: means for determining a utterance time of the sentence; displaying the sentence; and displaying the sentence for each predetermined unit in the sentence. A storage medium storing a program for functioning as means for changing the color of the sentence according to the utterance time. 22. The syllable constituting the sentence, wherein the unit is:
The storage medium according to any one of claims 18 to 21, wherein the storage medium is a pause phrase or an accent phrase. 23. A computer for recording a voice of a speaker reading a predetermined sentence, comprising: means for determining a utterance time of the sentence; displaying the sentence by continuously moving the sentence; A storage medium storing a program to function as means for displaying a fixed mark indicating a portion to be uttered. 24. A computer for recording a voice of a speaker reading a predetermined sentence, comprising: a computer for determining a utterance time of the sentence; a means for displaying the sentence and generating a sound based on the utterance time. A storage medium that stores a program that functions as a and.