Optimized local feature extraction for automatic speech recognition
US6513004B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 24, 1999 |
| Grant date | Jan 28, 2003 |
| Priority date | — |
| Expiry date | Nov 24, 2019 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/27
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The acoustic speech signal is decomposed into wavelets arranged in an asymmetrical tree data structure from which individual nodes may be selected to best extract local features, as needed to model specific classes of sound units. The wavelet packet transformation is smoothed through integration and compressed to apply a non-linearity prior to discrete cosine transformation. The resulting subband features such as cepstral coefficients may then be used to construct the speech recognizer's speech models. Using the local feature information extracted in this manner allows a single recognizer to be optimized for several different classes of sound units, thereby eliminating the need for parallel path recognizers.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.