JP2006119377A - Voice input device and method, and program and storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a voice input device and method, and a program and a storage medium with which voice input and voice recognition can be performed even with a voice whose sound volume is low, and which is not articulate. <P>SOLUTION: In the voice input device, a throat microphone 1 is equipped near a throat in which the vocal cords of a human exist, and detects vibration of the vocal cords corresponding to a voice when the human uttered the voice and converts the vibration into an electric signal. The converted electric signal is transmitted to an A/D conversion part 2. The A/D conversion part 2 converts an analog signal transmitted from the throat microphone 1 into a digital signal to transmit it to a feature extracting part 3. The feature extracting part 3 performs the frequency modulation of the digital signal, and extracts feature parameters in a frequency region, and transmits parameters to a collation part 4 as a string of uttered feature parameters. The collation part 4 compares the string of the parameters with standard patterns of respective words stored in a recognition dictionary part 5, and selects a word approximated most. A CPU 6 processes the word selected in the recognition dictionary 5 as an input character. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a voice input device and method, a program, and a storage medium, and more particularly, to a voice input / output device and method, and a program and a storage medium that use the vibration of a vocal cord when a person utters a voice.

  Conventionally, keyboards, touch panels, mice, etc. have been used as general input means such as electronic devices, but in recent years there has been a demand for simpler input means, and input devices by handwritten character recognition using a touch panel, An input device using voice recognition has been devised.

For example, an input device using speech recognition disclosed in Patent Document 1 converts air vibration caused by speech into an electrical signal using a microphone or the like, samples the signal waveform, and outputs the sampled data and a standard pattern. Characters are input by performing comparative analysis and recognizing speech uttered by a person.
Japanese Patent Laid-Open No. 3-120595

  However, the conventional voice recognition device has a problem that a person must actually emit a sound of a certain volume, and when there is another person around, the person is inconvenienced or he / she feels embarrassed. In addition, when the surrounding noise (noise) is large, there is a problem that the recognition rate is lowered.

  An object of the present invention is to provide a voice input device and method, a program, and a storage medium that can perform voice input and voice recognition even with low-volume and unclear voice.

  In order to achieve the above object, a voice input device according to claim 1 is provided with a conversion means for detecting a vibration of a vocal cord when a person utters a sound and converting the vibration into an electric signal; Recognizing means for recognizing a voice uttered as a voice signal.

  The voice input method according to claim 3, wherein a conversion step of detecting a vocal cord vibration when a person utters a voice and converting it into an electric signal, and a voice uttered by the person from the converted electric signal are recognized as a voice signal. And a recognition process.

  According to a fifth aspect of the present invention, there is provided a control program that causes a computer to execute the voice input method according to the third aspect.

  A computer-readable storage medium according to a sixth aspect stores the control program according to the fifth aspect.

  According to the present invention, the vibration of the vocal cord when a person utters a voice is detected and converted into an electric signal, and the voice uttered by the person is recognized as a voice signal from the converted electric signal. Voice input and voice recognition can be performed even at low volume without being heard and without being affected by ambient noise.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram schematically showing the configuration of the voice input device according to the first embodiment of the invention.

  In the voice input device of FIG. 1, the throat microphone 1 (conversion means) is mounted near the throat where a person's vocal cord is located, and when the person utters a voice (the voice may be inaudible to the surroundings). Is detected, and the vibration is converted into an electrical signal. The converted electrical signal is sent to the A / D converter 2. The A / D conversion unit 2 converts the analog signal sent from the throat microphone 1 into a digital signal, and sends the digital signal to the feature extraction unit 3. The feature extraction unit 3 performs frequency conversion on the digital signal, extracts feature parameters in the frequency domain, and sends them to the collation unit 4 (recognition means) as a sequence of spoken feature parameters. The matching unit 4 compares the standard pattern of each word stored in the recognition dictionary unit 5 and selects the closest word. The data used in this standard pattern is not data used in normal speech recognition but data created by directly detecting vibration of the vocal cords. The CPU 6 processes the word selected by the recognition dictionary unit 5 as an input character. As an example of the processing, the CPU 6 inputs a person's name, retrieves the person's data (for example, customer data in a portable information terminal used by a salesperson) from the memory 7, and displays the display unit 8. To display. The key input unit 9 is a cursor key for moving to the next screen when there is data that cannot be displayed on one screen, such as cursor movement and enter key, or when selecting an item when inputting customer data. Is used. In addition, when the input data or the like is correctly recognized and confirmed after the voice input, the enter key is entered and confirmed. As a result, voice input and voice recognition can be performed even with low-volume and unclear voice without being heard by other people around and without being affected by ambient noise.

  FIG. 2 is a block diagram schematically showing the configuration of the voice input device according to the second embodiment of the invention.

  The configuration of the present embodiment is the configuration of FIG. 1 in that it has voice data 10, a voice synthesis unit 11, a D / A conversion unit 12, and a speaker 12 instead of the display unit 8 and the key input unit 9 of FIG. Unlike this, the other components are basically the same as the configuration of FIG. 1, and the same components as those of FIG.

  In the voice input / output device of FIG. 2, the CPU 6 temporarily stores the words recognized by the collation unit 4 in the memory 107, and at the same time, concatenates the words input so far and performs syntax analysis. When it is recognized as one sentence, the voice data such as reading, accent, intonation, pause, etc. optimized for the sentence is read from the voice data unit 10 and sent to the voice synthesis unit 11 (synthesis unit). The voice synthesizer 11 synthesizes a voice waveform based on the sent voice data and sends it to the D / A converter 12. The D / A converter 12 converts the digital signal into an analog signal, and the analog audio signal is output as audio by the speaker 13 (output means). Thereby, a person who cannot utter a sound at a sufficient volume or a person who can utter only a low volume can clearly speak at a sufficient volume. Although not shown, the volume can be adjusted if a volume or the like is provided.

  Another object of the present invention is to supply a storage medium (or recording medium) in which a program code of software for realizing the functions of the above-described embodiments is recorded to a system or apparatus, and to perform computer (or CPU or MPU) of the system or apparatus. Needless to say, this is also achieved by reading and executing the program code stored in the storage medium.

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

  Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an operating system (OS) or the like running on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

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

  The above-described program only needs to be able to realize the functions of the above-described embodiments by a computer, and the form includes forms such as object code, a program executed by an interpreter, and script data supplied to the OS. But you can.

  As a recording medium for supplying the program, for example, RAM, NV-RAM, floppy (registered trademark) disk, optical disk, magneto-optical disk, CD-ROM, MO, CD-R, CD-RW, DVD (DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), magnetic tape, non-volatile memory card, other ROM, etc. may be used as long as they can store the above programs. Alternatively, the program is supplied by downloading from another computer or database (not shown) connected to the Internet, a commercial network, a local area network, or the like.

1 is a block diagram schematically showing a configuration of a voice input device according to a first embodiment of the present invention. It is a block diagram which shows roughly the structure of the audio | voice input apparatus which concerns on the 2nd Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Throat microphone 2 A / D conversion part 3 Feature extraction part 4 Collation part 5 Recognition dictionary part 6 CPU
7 Memory 8 Display unit 9 Key input unit 10 Audio data 11 Speech synthesis unit 12 D / A conversion unit 13 Speaker

Claims (6)

  Characterized in that it comprises conversion means for detecting vibration of a vocal cord when a person utters a voice and converting it into an electric signal, and recognition means for recognizing a voice uttered by a person from the converted electric signal as a voice signal. Voice input device.   2. The voice input device according to claim 1, further comprising: a synthesis unit that synthesizes the voice signal recognized by the recognition unit; and an output unit that outputs the synthesized voice signal as a voice.   A conversion step of detecting vibration of a vocal cord when a person utters a voice and converting it into an electric signal; and a recognition step of recognizing a voice uttered by a person from the converted electric signal as a voice signal. Voice input method.   4. The voice input method according to claim 3, further comprising: a synthesis step of synthesizing the voice signal recognized by the recognition step; and an output step of outputting the synthesized voice signal as voice.   A control program for causing a computer to execute the voice input method according to claim 3.   A computer-readable storage medium storing the control program according to claim 5.

Images