# US 2002/0120444 A1 · Speech recognition method

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

- Number: US 2002/0120444 A1
- Document ID: US20020120444A1
- Status: Published application
- Kind: A1
- Application number: 09/961,954
- Filed: 2001-09-24
- Published: 2002-08-29
- Earliest claimed: 2000-09-27
- Assignees: Koninklijke Philips Electronics N.V.
- Inventors: Henrik Botterweck
- Web page: https://patentgrep.com/patent/US20020120444A1

## CPC

- G10L 15/07: to the speaker
- G06F 18/2135: based on approximation criteria, e.g. principal component analysis
- G06F 18/24155: {Bayesian classification}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A speech recognition method is described in which a basic set of models is adapted to a current speaker on account of the speaker's already noticed speech data. The basic set of models comprises models for different acoustic units. The models are described each by a plurality of model parameters. The basic set of models is then represented by a supervector in a high-dimensional vector space (model space), the supervector being formed by a concatenation of the plurality of the model parameters of the models of the basic set of models. The adaptation of this basic set of models to the speaker is effected in the model space by means of a MAP method in which an asymmetric distribution in the model space is selected as an a priori distribution for the MAP method.

## Claims

### Claim 1

A speech recognition method in which a basic set of models, which comprises models for various acoustic units, while the models are described by a plurality of model parameters, is adapted to a current speaker based on already observed speech data of this speaker, characterized
in that the basic set of models is represented by a supervector in a high-dimensional vector space (model space), where the supervector is formed by concatenation of the plurality of model parameters of the models of the basic set of models, and this basic set of models in the model space is adapted to the speakers by means of a MAP method, while an asymmetrical distribution in the model space is chosen as an a priori distribution for the MAP method.

### Claim 2 (depends on 1)

A method as claimed in claim 1, characterized
in that the a priori distribution is an asymmetrical Gaussian distribution.

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

A method as claimed in claim 1 or 2 characterized
in that the a priori distribution is chosen so that an adaptation in certain preferred directions in the model space takes place faster than perpendicularly to these preferred directions.

### Claim 4 (depends on 3)

A method as claimed in claim 3, characterized
in that the a priori distribution i n the direction of preferred directions and perpendicularly thereto has different variances.

### Claim 5

A method as claimed in one of the preceding claims, characterized
in that the preferred directions are chosen such that they represent the main directions within the model space along which the different speakers can be distinguished from each other.

### Claim 6 (depends on 5)

A method as claimed in claim 5, characterized
in that the preferred directions run along certain eigenspace basis vectors (Ee) of an eigenspace, which was determined based on training speech data of a plurality of training speakers.

### Claim 7 (depends on 6)

A method as claimed in claim 6, characterized
in that the eigenspace is determined in the following steps:
development of a common speaker-independent set of models for the training speakers while training speech data of the training speaker are used,
adaptation of the speaker-independent set of models to the individual training speaker to develop the speaker-dependent set of models while the respective training speech data of the individual training speakers are used,
establishing the assignment of the model parameters of the models (SI) of the speaker-independent set of models to the model parameters of the models (SD) of the speaker-dependent sets of models when the speaker-independent set of models are adapted to the individual training speakers,
showing a combined model for each speaker in a high-dimensional vector space by concatenation of a plurality of the model parameters of the models of the sets of models of the individual training speakers to a respective coherent supervector, where the concatenation of the plurality of model parameters of the individual sets of models to the supervectors is effected so that the model parameters of the models (SD) of the speaker-dependent sets of models, which are assigned to the same model parameters of the same model (SI) of the speaker-independent set of models are arranged at the respective positions of the respective supervectors,
performing a change of basis to reduce the model space to a speaker sub-space in which all the training speakers are represented,
performing a transformation of the vectors representing the training speakers in the speaker sub-space to gain eigenspace basis vectors (Ee) while the transformation utilizes a variability of the reduction criterion based on the vectors to be transformed.

### Claim 8 (depends on 7)

A method as claimed in claim 7, characterized
in that the basis of this speaker sub-space of orthogonalized difference vectors of the supervectors of the individual training speakers is spread out to a mean supervector.

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

A method as claimed in one of the claims 1 to 8, characterized
in that a set of mean models of speaker-dependent sets of models of the training speakers is used as a basic set of models.

### Claim 10 (depends on 6, 7, 8, 9)

A method as claimed in one of the claims 6 to 9, characterized
in that associated order attributes are determined for the eigenspace basis vectors ( Ee).

### Claim 11 (depends on 9, 10)

A method as claimed in claim 9 or 10, characterized
in that the eigenspace basis vectors are the eigenvectors of a correlation matrix determined by the supervectors and the order attributes are the eigenvalues belonging to the eigenvectors.

### Claim 12

A computer program with program code means for carrying out all the steps of a method as claimed in one of the preceding claims when the program is executed on a computer.

### Claim 13 (depends on 12)

A computer program with program code means as claimed in claim 12 which are stored on a computer-readable data carrier.
