Reducing streaming ASR model delay with self alignment
US12057124B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 15, 2021 |
| Grant date | Aug 6, 2024 |
| Priority date | — |
| Expiry date | Dec 15, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/16
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A streaming speech recognition model includes an audio encoder configured to receive a sequence of acoustic frames and generate a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The streaming speech recognition model also includes a label encoder configured to receive a sequence of non-blank symbols output by a final softmax layer and generate a dense representation. The streaming speech recognition model also includes a joint network configured to receive the higher order feature representation generated by the audio encoder and the dense representation generated by the label encoder and generate a probability distribution over possible speech recognition hypotheses. Here, the streaming speech recognition model is trained using self-alignment to reduce prediction delay by encouraging an alignment path that is one frame left from a reference forced-alignment frame.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.