Restructuring deep neural network acoustic models
US9728184B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 18, 2013 |
| Grant date | Aug 8, 2017 |
| Priority date | — |
| Expiry date | Jun 18, 2033 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/142
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A Deep Neural Network (DNN) model used in an Automatic Speech Recognition (ASR) system is restructured. A restructured DNN model may include fewer parameters compared to the original DNN model. The restructured DNN model may include a monophone state output layer in addition to the senone output layer of the original DNN model. Singular value decomposition (SVD) can be applied to one or more weight matrices of the DNN model to reduce the size of the DNN Model. The output layer of the DNN model may be restructured to include monophone states in addition to the senones (tied triphone states) which are included in the original DNN model. When the monophone states are included in the restructured DNN model, the posteriors of monophone states are used to select a small part of senones to be evaluated.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.