Method, device and program for extracting and recognizing voice

• US 20050203744A1
• Filed: 03/08/2005
• Published: 09/15/2005
• Est. Priority Date: 03/11/2004
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Tamura, Shinichi
• Granted Patent: US 7,440,892 B2
• Time in Patent Office: Days
• US Class Current: 704/265
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08

Abstract

In a method of extracting voice components free of noise components from voice signals input through a single microphone, a signal-decomposing unit extracts independent signal components from the voice signals input through a single microphone by using a plurality of filters that permit the passage of signal components of different frequency bands. A signal-synthesizing unit synthesizes the signal components according to a first rule to form a first synthesized signal, and synthesizes the signal components according to a second rule to form a second synthesized signal. The first and second rules are so determined that a difference becomes a maximum between the probability density function of the first synthesized signal and the probability density function of the second synthesized signal. An output selection unit selectively produces a synthesized signal having a large difference from the Gaussian distribution between the synthesized signals.

Claims

1. A method of extracting voice components from digital voice signals containing voice components and noise components, said method comprising:

extracting a plurality of kinds signal components from the digital voice signals by using a plurality of filters;

forming a first synthesized signal by synthesizing, according to a first rule, the signal components extracted, and forming a second synthesized signal by synthesizing, according to a second rule different from the first rule, the signal components extracted; and

selectively producing the synthesized signal expressing the feature of the voice components out of the first and second synthesized signals;

wherein the first and second rules are determined based on characteristic feature quantities of the first and second synthesized signals.

2. The method of claim 1, wherein the extracting of the plurality of kinds signal components further comprises setting impulse responses of the plurality of filters so that the signal components extracted by the filters become independent from, or uncorrelated to, each other.

3. The method of claim 1, wherein the filters are FIR type or IIR type digital band-pass filters.

4. The method of claim 1, wherein the first and second rules are so determined that a statistic feature quantity representing a difference between the probability density functions of the first and second synthesized signals becomes maximum.

5. The method of claims 1, wherein the first and second rules are so determined that a mutual data quantity of the first and second synthesized signals, which is the statistic feature quantity, becomes minimum.

6. The method of claim 1, wherein the first and second rules are determined based upon a statistic feature quantity representing a difference between probability density functions of the first and second synthesized signals, and upon a mutual data quantity of the first and second synthesized signals.

7. The method of claim 1, wherein the rules related to weighing the signal components extracted are determined as first and second rules, the signal components extracted at the step are weighed and added up according to the first rule to form the first synthesized signal, and the signal components extracted at the step are weighed and added up according to the second rule to form the second synthesized signal.

8. The method of claim 1, wherein the first synthesized signal and the second synthesized signal formed are evaluated for their differences from the Gaussian distribution, and the synthesized signal evaluated to have the greatest difference from the Gaussian distribution is selectively output as the synthesized signal expressing the voice component.

9. An apparatus for extracting voice to selectively extract the voice components from the digital voice signals containing voice components and noise components, said apparatus for extracting the voice comprising:

a plurality of filters;

extract means for extracting a plurality of kinds of signal components from the digital voice signals input from an external unit by using the plurality of filters;

first synthesizing means for forming a first synthesized signal by synthesizing the signal components extracted by the extract means according to a first rule;

second synthesizing means for forming a second synthesized signal by synthesizing the signal components extracted by the extract means according to a second rule different from the first rule;

selective output means for selectively producing the synthesized signal expressing the feature of the voice component between the first synthesized signal formed by the first synthesizing means and the second synthesized signal formed by the second synthesizing means; and

determining means for determining the first and second rules based on a statistic feature quantity of the first synthesized signal formed by the first synthesizing means and of the second synthesized signal formed by the second synthesizing means.

10. An apparatus for extracting the voice according to claim 9, wherein the extract means sets the impulse responses of the plurality of filters such that the signal components extracted by the filters become independent from, or uncorrelated to, each other, and extracts the plurality of kinds of signal components from the digital voice signals by using the plurality of filters.

11. An apparatus for extracting the voice according to claim 9, wherein the filters are the digital band-pass filters of the FIR type or the IIR type.

12. An apparatus for extracting the voice according to claim 9, wherein the first and second rules are so determined that a quantity expressing a difference between probability density functions of the first and second synthesized signals, which is a statistic feature quantity, becomes a maximum.

13. An apparatus for extracting the voice according to claim 9, wherein the first and second rules are so determined that mutual data quantity for the first and second synthesized signals, which is a statistic feature quantity, becomes a minimum.

14. An apparatus for extracting the voice according to claim 9, wherein the first and second rules are determined based upon the quantity expressing a difference between the probability density functions of the first and second synthesized signals, which is a statistic feature quantity, and upon the mutual data quantity for the first and second synthesized signals.

15. An apparatus for extracting the voice according to claim 9, wherein:

the determining means determines the rules related to weighing the signal components extracted by the extract means as the first and second rules;

the first synthesizing means weighs and adds up the signal components extracted by the extract means according to the first rule to form the first synthesized signal; and

the second synthesizing means weighs and adds up the signal components extracted by the extract means according to the second rule to form the second synthesized signal.

16. An apparatus for extracting the voice according to claim 9, wherein the selective output means includes evaluation means for evaluating the first synthesized signal formed by the first synthesizing means and the second synthesized signal formed by the second synthesizing means for their differences from the Gaussian distribution, and the synthesized signal evaluated by the evaluation means to possess the greatest difference from the Gaussian distribution is selectively output as the synthesized signal expressing the feature of the voice component.

17. An apparatus for recognizing the voice equipped with an apparatus for extracting the voice of claim 9, wherein the voice is recognized by using synthesized signals produced by the selective output means in the apparatus for extracting the voice.

18. A program, when installed in a computer, resulting in the computer realizing the function of:

a plurality of filters;

extract means for extracting a plurality of kinds of signal components from the digital voice signals containing voice components and noise components input from an external unit by using said plurality of filters;

first synthesizing means for forming a first synthesized signal by synthesizing the signal components extracted by said extract means according to a first rule;

second synthesizing means for forming a second synthesized signal by synthesizing the signal components extracted by said extract means according to a second rule different from the first rule;

selective output means for selectively producing the synthesized signal expressing the feature of the voice component between the first synthesized signal formed by the first synthesizing means and the second synthesized signal formed by the second synthesizing means; and

determining means for determining the first and second rules based on the statistic feature quantity of the first synthesized signal formed by the first synthesizing means and of the second synthesized signal formed by the second synthesizing means.