Token-wise training for attention based end-to-end speech recognition
US11636848B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 11, 2021 |
| Grant date | Apr 25, 2023 |
| Priority date | — |
| Expiry date | Jul 16, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0635
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of attention-based end-to-end (A-E2E) automatic speech recognition (ASR) training, includes performing cross-entropy training of a model, based on one or more input features of a speech signal, determining a posterior probability vector at a time of a first wrong token among one or more output tokens of the model of which the cross-entropy training is performed, and determining a loss of the first wrong token at the time, based on the determined posterior probability vector. The method further includes determining a total loss of a training set of the model of which the cross-entropy training is performed, based on the determined loss of the first wrong token, and updating the model of which the cross-entropy training is performed, based on the determined total loss of the training set.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.