Frame skipping with extrapolation and outputs on demand neural network for automatic speech recognition
US9520128B2 · kind B2 · utility
32Cited by
12References
21Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 23, 2014 |
| Grant date | Dec 13, 2016 |
| Priority date | — |
| Expiry date | Sep 28, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.