US5764853A — Voice recognition device and method using a (GGM)…

Claim 1

Independent Claim 270 words

A voice recognition device comprising: analyzing means for acoustically analyzing voice every predetermined frame unit to extract a feature vector X; converting means for subjecting the feature vector X output from said analyzing means to a predetermined conversion process; and recognition means for recognizing the voice on the basis of a new feature vector output from said conversion means, wherein said conversion means conducts the predetermined conversion processing according to a mapping F from an N-dimensional vector space Ω N to an M-dimensional vector space Ω M , the feature vector X is a vector on the N-dimensional vector space Ω N , and the function f m (X) of an mth component of the mapping F is represented by the following linear summation of the products of complete component functions g m k (X) of L m determined on the basis of the distribution of the learning sample S q (=(S 0 q , S 1 q , S 2 q , . . . , S N-1 q )) on the N-dimensional measurable vector space which is classified into categories C q (q=0, 1, 2, . . . , Q-1) of Q, and coefficients c m k of L m : ##EQU12## wherein when teacher vectors T q (=(t 0 q , t 1 q , t 2 q , . . . , t M-1 q )) on an M-dimensional measurable vector space Ω M for the categories C q of Q are provided and a predetermined estimation function J is calculated, the coefficient c m k is determined so as to minimize the estimation function J.

Claim 2

Dependent Claim 270 words

A voice recognition device comprising: analyzing means for acoustically analyzing voice every predetermined frame unit to extract a feature vector X; converting means for subjecting the feature vector X output from said analyzing means to a predetermined conversion process; and recognition means for recognizing the voice on the basis of a new feature vector output from said conversion means, wherein said conversion means conducts the predetermined conversion processing according to a mapping F from an N-dimensional vector space Ω N to an M-dimensional vector space Ω M , the feature vector X is a vector on the N-dimensional vector space Ω N , and the function f m (X) of an mth component of the mapping F is represented by the following linear summation of the products of complete component functions g m k (X) of L m determined on the basis of the distribution of the learning sample S q (=(S 0 q , S 1 q , S 2 q , . . . , S N-1 q )) on the N-dimensional measurable vector space which is classified into categories C q (q=0, 1, 2, . . . , Q-1) of Q, and coefficients c m k of L m : ##EQU12## wherein when teacher vectors T q (=(t 0 q , t 1 q , t 2 q , . . . , t M-1 q )) on an M-dimensional measurable vector space Ω M for the categories C q of Q are provided and a predetermined estimation function J is calculated, the coefficient c m k is determined so as to minimize the estimation function J.

Claim 3

Dependent Claim 71 words

The voice recognition device as claimed in claim 1, wherein when a calculation of an expected value of the function f m (X) over all the elements of the learning sample S q is represented by E{XεS q }{f(X)}, the estimation function J is represented as follows: ##EQU13## the categories C q of Q correspond to Q types of phonemes, and the learning sample S q correspond to labelled voice data.

Claim 4

Dependent Claim 21 words

The voice recognition device as claimed in claim 2, wherein each function g m k (X) is set to a monomial.

Claim 5

Dependent Claim 40 words

The voice recognition device as claimed in claim 2, wherein the dimension M of the vector space after the conversion by the mapping F is equal to the total number Q of the categories C q corresponding to the phonemes.

Claim 6

Dependent Claim 39 words

The voice recognition device as claimed in claim 2, wherein each of the teacher vectors T q is an unit vector in the M-dimensional vector space, and the teacher vectors T q of Q are orthogonal to each other.

Claim 7

Dependent Claim 49 words

The voice recognition device as claimed in claim 2, further including bundling means for bundling feature vectors X of plural frames, each of which is output every predetermined frame unit from said analyzing means, and then supplying bundled feature vectors as a feature vector X to said conversion means.

Claim 8

Dependent Claim 17 words

The voice recognition device as claimed in claim 2, wherein the feature vector X comprises LPC spectrum.

Claim 9

Dependent Claim 22 words

The voice recognition device as claimed in claim 2, wherein the feature vector X comprises power every predetermined band width of voice.

Claim 10

Dependent Claim 39 words

The voice recognition device as claimed in claim 2, wherein said recognition means recognizes voice on the basis of both the new feature vector output from said converting means and said feature vector X output from said analyzing means.

Claim 11

Dependent Claim 66 words

The voice recognition device as claimed in claim 2, wherein said analyzing means acoustically analyzes the voice and extracts the feature vector X and another feature vector which is different from the feature vector X, and said recognizing means recognizes the voice on the basis of both the new feature vector output from said conversion means and the other feature vector output from said analyzing means.

Claim 12

Dependent Claim 40 words

The voice recognition device as claimed in claim 10, wherein the other feature vector is set to the difference between respective feature vectors X extracted from two frames which are spaced away from each other by a predetermined frame number.

Claim 13

Dependent Claim 24 words

The voice recognition device as claimed in claim 2, wherein said recognition means recognizes the voice according to an HMM (Hidden Markov Models) method.

Claim 14

Dependent Claim 54 words

The voice recognition device as claimed in claim 12, further including vector quantization means for vector-quantizing a vector supplied to said recognition means to output a predetermined code, wherein said recognition means recognizes the voice on the basis of the predetermined code output from said vector quantization means according to the discrete HMM method.

Claim 15

Dependent Claim 278 words

A voice recognition method comprising: a voice analyzing step for acoustically analyzing voice every predetermined frame unit to extract a feature vector X; a vector conversion step for subjecting the feature vector X extracted in said analyzing step to a predetermined conversion process; and a voice recognition step for recognizing the voice on the basis of the new feature vector output in said vector conversion step, wherein the predetermined conversion processing is conducted according to a mapping F from an Ndimensional vector space Ω N to an M-dimensional vector space Ω M in said vector conversion step, the feature vector X is a vector on the N-dimensional vector space Ω N , and the function f m (X) of an m-th component of the mapping F is represented by the following linear summation of the products of complete component functions g m k (X) of L m determined on the basis of the distribution of the learning sample S q (=(S 0 q , S 1 q , S 2 q , . . . , S N-1 q )) on the N-dimensional measurable vector space which is classified into categories C q (q=0, 1, 2, . . . , Q-1) of Q, and coefficients c m k of L m : ##EQU14## wherein when teacher vectors T q (=(t 0 q , t 1 q , t 2 q , . . . , t M-1 q )) on an M-dimensional measurable vector space gm for the categories C q of Q are provided and a predetermined estimation function J is calculated, the coefficient C m k is determined so as to minimize the estimation function J.

Claim 16

Dependent Claim 278 words

A voice recognition method comprising: a voice analyzing step for acoustically analyzing voice every predetermined frame unit to extract a feature vector X; a vector conversion step for subjecting the feature vector X extracted in said analyzing step to a predetermined conversion process; and a voice recognition step for recognizing the voice on the basis of the new feature vector output in said vector conversion step, wherein the predetermined conversion processing is conducted according to a mapping F from an Ndimensional vector space Ω N to an M-dimensional vector space Ω M in said vector conversion step, the feature vector X is a vector on the N-dimensional vector space Ω N , and the function f m (X) of an m-th component of the mapping F is represented by the following linear summation of the products of complete component functions g m k (X) of L m determined on the basis of the distribution of the learning sample S q (=(S 0 q , S 1 q , S 2 q , . . . , S N-1 q )) on the N-dimensional measurable vector space which is classified into categories C q (q=0, 1, 2, . . . , Q-1) of Q, and coefficients c m k of L m : ##EQU14## wherein when teacher vectors T q (=(t 0 q , t 1 q , t 2 q , . . . , t M-1 q )) on an M-dimensional measurable vector space gm for the categories C q of Q are provided and a predetermined estimation function J is calculated, the coefficient C m k is determined so as to minimize the estimation function J.

Claim 17

Dependent Claim 71 words

The voice recognition method as claimed in claim 14, wherein when a calculation of an expected value of the function f m (X) over all the elements of the learning sample S q is represented by E{XεS q }{f(X)}, the estimation function J is represented as follows: ##EQU15## the categories C q of Q correspond to Q types of phonemes, and the learning sample S q correspond to labelled voice data.

Claim 18

Dependent Claim 21 words

The voice recognition method as claimed in claim 15, wherein each function g m k (X) is set to a monomial.

Claim 19

Dependent Claim 40 words

The voice recognition method as claimed in claim 15, wherein the dimension M of the vector space after the conversion by the mapping F is equal to the total number Q of the categories C q corresponding to the phonemes.

Claim 20

Dependent Claim 39 words

The voice recognition method as claimed in claim 15, wherein each of the teacher vectors T q is an unit vector in the M-dimensional vector space, and the teacher vectors T q of Q are orthogonal to each other.

Claim 21

Dependent Claim 51 words

The voice recognition method as claimed in claim 15, further comprising a bundling step for bundling feature vectors X of plural frames, each of which is output every predetermined frame unit in said voice analyzing step, and then supplying bundled feature vectors as a feature vector X to said conversion means.

Claim 22

Dependent Claim 17 words

The voice recognition method as claimed in claim 15, wherein the feature vector X comprises LPC spectrum.

Claim 23

Dependent Claim 22 words

The voice recognition method as claimed in claim 15, wherein the feature vector X comprises power every predetermined band width of voice.

Claim 24

Dependent Claim 43 words

The voice recognition method as claimed in claim 15, wherein in said voice recognition step, voice is recognized on the basis of both the new feature vector output from said conversion step and said feature vector X output from said voice analyzing step.

Claim 25

Dependent Claim 73 words

The voice recognition method as claimed in claim 15, wherein in said voice analyzing step, the voice is acoustically analyzed to extract the feature vector X and another feature vector which is different from the feature vector X, and in said voice recognizing step the voice is recognized on the basis of both the new feature vector output from said conversion step and the other feature vector output from said voice analyzing step.

Claim 26

Dependent Claim 40 words

The voice recognition method as claimed in claim 23, wherein the other feature vector is set to the difference between respective feature vectors X extracted from two frames which are spaced away from each other by a predetermined frame number.

Claim 27

Dependent Claim 25 words

The voice recognition method as claimed in claim 15, wherein in said recognition the voice is recognized according to an HMM (Hidden Markov Models) method.

Claim 28

Dependent Claim 52 words

The voice recognition method as claimed in claim 25, wherein said voice recognizing step includes a vector quantization step for vector-quantizing the supplied vector to output a predetermined code, the voice being recognized on the basis of the predetermined code output from said vector quantization step according to the discrete HMM method.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2001-06-08	2001-12-08	2002-06-09	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2005-06-08	2005-12-08	2006-06-09	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2009-06-08	2009-12-08	2010-06-09	$7700.00	Window Closed / Lapsed

Voice recognition device and method using a (GGM) Guaranteed Global minimum Mapping

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag