Fast emit low-latency streaming ASR with sequence-level emission regularization utilizing forward and backward probabilities between nodes of an alignment lattice
US12094453B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 9, 2021 |
| Grant date | Sep 17, 2024 |
| Priority date | — |
| Expiry date | Sep 25, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/187
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.