Attention-based joint acoustic and text on-device end-to-end model
US11594212B2 · kind B2 · utility
1Cited by
2References
21Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 21, 2021 |
| Grant date | Feb 28, 2023 |
| Priority date | — |
| Expiry date | May 9, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0635
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving a training example for a listen-attend-spell (LAS) decoder of a two-pass streaming neural network model and determining whether the training example corresponds to a supervised audio-text pair or an unpaired text sequence. When the training example corresponds to an unpaired text sequence, the method also includes determining a cross entropy loss based on a log probability associated with a context vector of the training example. The method also includes updating the LAS decoder and the context vector based on the determined cross entropy loss.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.