# US 2001/0025276 A1 · Model adaptive apparatus and model adaptive method, recording medium, and pattern recognition apparatus

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2001/0025276 A1
- Document ID: US20010025276A1
- Status: Published application
- Kind: A1
- Application number: 09/748,471
- Filed: 2000-12-26
- Published: 2001-09-27
- Earliest claimed: 1999-12-28
- Assignees: Sony Corporation
- Inventors: Hongchang Pao
- Web page: https://patentgrep.com/patent/US20010025276A1

## CPC

- G10L 15/065: Adaptation
- G10L 15/20: Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

In order to improve recognition performance, a no-speech sound model correction section performs an adaptation of a no-speech sound model which is a sound model representing a no-speech state on the basis of input data observed in an interval immediately before a speech recognition interval for the object of speech recognition and the degree of freshness representing the recentness of the input data.

## Claims

### Claim 1

A model adaptive apparatus for performing an adaptation of a model used in pattern recognition which classifies input data in a time series into one of a predetermined number of models, said model adaptive apparatus comprising:
data extraction means for extracting said input data, corresponding to a predetermined model, which is observed in a predetermined interval, and for outputting the data as extracted data; and
model adaptation means for performing an adaptation of said predetermined model on the basis of the extracted data in said predetermined interval and the degree of freshness representing the recentness of the extracted data.

### Claim 2 (depends on 1)

A model adaptive apparatus according to claim 1, wherein said pattern recognition is performed based on a feature distribution in a feature space of said input data.

### Claim 3 (depends on 1, 2)

A model adaptive apparatus according to claim 1 or 2, wherein said model adaptation means performs an adaptation of said predetermined model by using, as said freshness, a function in which the value changes in such a manner as to correspond to the time-related position of said extracted data in said predetermined interval.

### Claim 4 (depends on 3)

A model adaptive apparatus according to claim 3, wherein said function is a monotonically increasing function which increases as time elapses.

### Claim 5 (depends on 4)

A model adaptive apparatus according to claim 4, wherein said function is a linear or nonlinear function.

### Claim 6 (depends on 4)

A model adaptive apparatus according to claim 4, wherein said function takes discrete values or continuous values.

### Claim 7 (depends on 4)

A model adaptive apparatus according to claim 4, wherein said function is a second-order function, a third-order function, or a higher-order function.

### Claim 8 (depends on 4)

A model adaptive apparatus according to claim 4, wherein said function is a logarithmic function.

### Claim 9 (depends on 1, 2, 3, 4, 5, 6, 7, 8)

A model adaptive apparatus according to any one of claims 1 to 8, wherein said input data is speech data.

### Claim 10 (depends on 9)

A model adaptive apparatus according to claim 9, wherein said predetermined model is a sound model representing noise in an interval which is not a speech segment.

### Claim 11 (depends on 1, 2, 3, 4, 5, 6, 7, 8, 9, 10)

A model adaptive apparatus according to any one of claims 1 to 10, wherein said data extraction means comprise:
framing means (2) having an input for receiving a source (1) of speech and/or environmental noise and for producing in response data frames;
noise observation interval extraction means (3) for extracting a noise vector for a number (M) of frames in a noise observation interval (Tn);
feature extraction means (5) responsive to said noise vector (a) and to an observation vector (a) in a speech recognition interval to produce a feature vector (y); and
no-speech sound model correction means (7) responsive to said noise vector.

### Claim 12 (depends on 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11)

A model adaptive apparatus according to any one of claims 1 to 11, further comprising:
power spectrum analysis means (11) for receiving said extracted data;
noise characteristic calculation means (13) responsive to environmental noise; and
feature distribution parameter calculation means (12) for producing a feature distribution parameter (Z) in response to said power spectrum analysis means and said noise characteristic calculation means.

### Claim 13 (depends on 12)

A model adaptive apparatus according claim 12, further comprising:
a plurality of identification function computation means (21-s, 21-1-21k) of which one at least receives a no-speech model, said means receiving said feature distribution parameter (Z) and producing in response a respective identification function (Gs(Z), G1(Z)-Gk(Z)); and
determination mean (22) responsive to said identification functions to produce a recognition result on the basis of a closest match.

### Claim 14 (depends on 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)

A model adaptive apparatus according to any one of claims 1 to 13, further comprising:
feature extraction means for extracting the features of said input data;
storage means for storing a predetermined number of models into which said input data is to be classified; and
classification means for classifying the features of said input data, corresponding to a predetermined model, which is observed in a predetermined interval, and for outputting the data as extracted data.

### Claim 15

A pattern recognition apparatus for classifying input data in a time series into one of a predetermined number of models, said pattern recognition apparatus comprising:
feature extraction means for extracting the features of said input data;
storage means for storing said predetermined number of models;
classification means for classifying the features of said input data into one of said predetermined number of models;
data extraction means for extracting said input data, corresponding to a predetermined model, which is observed in a predetermined interval, and for outputting the data as extracted data; and
model adaptation means for performing an adaptation of said predetermined model on the basis of the extracted data in said predetermined interval and the degree of freshness representing the recentness of the extracted data.

### Claim 16

A model adaptive method for performing an adaptation of a model used in pattern recognition which classifies input data in a time series into one of a predetermined number of models, said model adaptive method comprising:
a data extraction step of extracting said input data, corresponding to a predetermined model, which is observed in a predetermined interval, and of outputting the data as extracted data; and
a model adaptation step of performing an adaptation of said predetermined model on the basis of the extracted data in said predetermined interval and the degree of freshness representing the recentness of the extracted data.

### Claim 17

A recording medium having recorded therein a program for causing a computer to perform an adaptation of a model used in pattern recognition which classifies input data in a time series into one of a predetermined number of models, said program comprising:
a data extraction step of extracting said input data, corresponding to a predetermined model, which is observed in a predetermined interval, and of outputting the data as extracted data; and
a model adaptation step of performing an adaptation of said predetermined model on the basis of the extracted data in said predetermined interval and the degree of freshness representing the recentness of the extracted data.
