Exploiting heterogeneous data in deep neural network-based speech recognition systems
US9454958B2 · kind B2 · utility
28Cited by
3References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 7, 2013 |
| Grant date | Sep 27, 2016 |
| Priority date | — |
| Expiry date | Apr 13, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Technologies pertaining to training a deep neural network (DNN) for use in a recognition system are described herein. The DNN is trained using heterogeneous data, the heterogeneous data including narrowband signals and wideband signals. The DNN, subsequent to being trained, receives an input signal that can be either a wideband signal or narrowband signal. The DNN estimates the class posterior probability of the input signal regardless of whether the input signal is the wideband signal or the narrowband signal.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.