# US 2015/0088498 A1 · Low latency real-time vocal tract length normalization

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

- Number: US 2015/0088498 A1
- Document ID: US20150088498A1
- Status: Published application
- Kind: A1
- Application number: 14/554,339
- Filed: 2014-11-26
- Published: 2015-03-26
- Earliest claimed: 2005-01-12
- Assignees: AT&T Intellectual Property II, L.P.
- Applicants: At&T Intellectual Property II, L.P.
- Inventors: Vincent GOFFIN; Andrej LJOLJE; Murat Saraclar
- Web page: https://patentgrep.com/patent/US20150088498A1

## CPC

- G10L 15/063: {Training}
- G10L 15/10: using distance or distortion measures between unknown speech and reference templates
- G10L 15/12: using dynamic programming techniques, e.g. dynamic time warping [DTW]
- G10L 17/08: Use of distortion metrics or a particular distance between probe pattern and reference templates
- G10L 17/04: Training, enrolment or model building
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method and system for training an automatic speech recognition system are provided. The method includes separating training data into speaker specific segments, and for each speaker specific segment, performing the following acts: generating spectral data, selecting a first warping factor and warping the spectral data, and comparing the warped spectral data with a speech model. The method also includes iteratively performing the steps of selecting another warping factor and generating another warped spectral data, comparing the other warped spectral data with the speech model, and if the other warping factor produces a closer match to the speech model, saving the other warping factor as the best warping factor for the speaker specific segment. The system includes modules configured to control a processor in the system to perform the steps of the method.

## Claims

### Claim 1

A method comprising:
performing, for a speaker specific segment of training data:
generating spectral data representative of the speaker specific segment, the spectral data comprising a plurality of warping factors;
selecting a first warping factor as a best warping factor from the plurality of warping factors based on a determination made during speech recognition of the speaker specific segment; and
generating a warped spectral data representation of the spectral data using the first warping factor;
iteratively carrying out, until a comparison indicates a warping factor difference below a threshold, the operations of:
generating an other warped spectral data representation using other warping factors;
comparing the other warped spectral data representation to the warped spectral data representation, to yield the comparison; and
when the other warping factor produces a closer match to the vocal tract length normalized acoustic model, saving the other warping factor as a best warping factor for the speaker specific segment; and
training a new acoustic model using a warped spectral data representation of all the training data that is generated using the best warping factor for each of the speaker specific segments.

### Claim 2 (depends on 1)

The method of claim 1, wherein the comparison further requires a predetermined amount of total speech having been used to select the best warping factor.

### Claim 3 (depends on 1)

The method of claim 1, wherein the comparison further a difference between a latest warping factor and a preceding warping factor being smaller than a predetermined amount.

### Claim 4 (depends on 1)

The method of claim 1, wherein the spectral data is a short-term magnitude spectrum of the speaker specific segment.

### Claim 5 (depends on 1)

The method of claim 1, wherein the spectral data comprises a spectral axis modified by the warping factor.

### Claim 6 (depends on 5)

The method of claim 5, wherein the new acoustic model comprises a vocal tract length normalized acoustic model based on the spectral axis modified by the warping factor.

### Claim 7 (depends on 1)

The method of claim 1, wherein the vocal tract length normalized acoustic model is initially a generic acoustic model.

### Claim 8

A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising:
performing, for a speaker specific segment of training data:
generating spectral data representative of the speaker specific segment,
the spectral data comprising a plurality of warping factors;
selecting a first warping factor as a best warping factor from the plurality of warping factors based on a determination made during speech recognition of the speaker specific segment; and
generating a warped spectral data representation of the spectral data using the first warping factor;
iteratively carrying out, until a comparison indicates a warping factor difference below a threshold, the operations of:
generating an other warped spectral data representation using other warping factors;
comparing the other warped spectral data representation to the warped spectral data representation, to yield the comparison; and
when the other warping factor produces a closer match to the vocal tract length normalized acoustic model, saving the other warping factor as a best warping factor for the speaker specific segment; and
training a new acoustic model using a warped spectral data representation of all the training data that is generated using the best warping factor for each of the speaker specific segments.

### Claim 9 (depends on 8)

The system of claim 8, wherein the comparison further requires a predetermined amount of total speech having been used to select the best warping factor.

### Claim 10 (depends on 8)

The system of claim 8, wherein the comparison further a difference between a latest warping factor and a preceding warping factor being smaller than a predetermined amount.

### Claim 11 (depends on 8)

The system of claim 8, wherein the spectral data is a short-term magnitude spectrum of the speaker specific segment.

### Claim 12 (depends on 8)

The system of claim 8, wherein the spectral data comprises a spectral axis modified by the warping factor.

### Claim 13 (depends on 12)

The system of claim 12, wherein the new acoustic model comprises a vocal tract length normalized acoustic model based on the spectral axis modified by the warping factor.

### Claim 14 (depends on 8)

The system of claim 8, wherein the vocal tract length normalized acoustic model is initially a generic acoustic model.

### Claim 15

A computer-readable storage device having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:
performing, for a speaker specific segment of training data:
generating spectral data representative of the speaker specific segment, the spectral data comprising a plurality of warping factors;
selecting a first warping factor as a best warping factor from the plurality of warping factors based on a determination made during speech recognition of the speaker specific segment; and
generating a warped spectral data representation of the spectral data using the first warping factor;
iteratively carrying out, until a comparison indicates a warping factor difference below a threshold, the operations of:
generating an other warped spectral data representation using other warping factors;
comparing the other warped spectral data representation to the warped spectral data representation, to yield the comparison; and
when the other warping factor produces a closer match to the vocal tract length normalized acoustic model, saving the other warping factor as a best warping factor for the speaker specific segment; and
training a new acoustic model using a warped spectral data representation of all the training data that is generated using the best warping factor for each of the speaker specific segments.

### Claim 16 (depends on 15)

The computer-readable storage device of claim 15, wherein the comparison further requires a predetermined amount of total speech having been used to select the best warping factor.

### Claim 17 (depends on 15)

The s computer-readable storage device of claim 15, wherein the comparison further a difference between a latest warping factor and a preceding warping factor being smaller than a predetermined amount.

### Claim 18 (depends on 15)

The computer-readable storage device of claim 15, wherein the spectral data is a short-term magnitude spectrum of the speaker specific segment.

### Claim 19 (depends on 15)

The computer-readable storage device of claim 15, wherein the spectral data comprises a spectral axis modified by the warping factor.

### Claim 20 (depends on 19)

The computer-readable storage device of claim 19, wherein the new acoustic model comprises a vocal tract length normalized acoustic model based on the spectral axis modified by the warping factor.
