Shared hidden layer combination for speech recognition systems
US9520127B2 · kind B2 · utility
6Cited by
17References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 29, 2014 |
| Grant date | Dec 13, 2016 |
| Priority date | — |
| Expiry date | May 1, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/025
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Providing a framework for merging automatic speech recognition (ASR) systems having a shared deep neural network (DNN) feature transformation is provided. A received utterance may be evaluated to generate a DNN-derived feature from the top hidden layer of a DNN. The top hidden layer output may then be utilized to generate a network including a bottleneck layer and an output layer. Weights representing a feature dimension reduction may then be extracted between the top hidden layer and the bottleneck layer. Scores may then be generated and combined to merge the ASR systems which share the DNN feature transformation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.