Method and apparatus for producing acoustic model
US6842734B2 · kind B2 · utility
12Cited by
3References
8Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 14, 2001 |
| Grant date | Jan 11, 2005 |
| Priority date | — |
| Expiry date | Jul 26, 2023 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0638
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In an acoustic model producing apparatus, a plurality of noise samples are categorized into clusters so that a number of the clusters is smaller than that of noise samples. A noise sample is selected in each of the clusters to set the selected noise samples to second noise samples for training. On the other hand, untrained acoustic models are stored on a storage unit so that the untrained acoustic models are trained by using the second noise samples for training, thereby producing trained acoustic models for speech recognition so as to produce a trained acoustic model for speech recognition.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.