Language agnostic multilingual end-to-end streaming on-device ASR system
US12183322B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 22, 2022 |
| Grant date | Dec 31, 2024 |
| Priority date | — |
| Expiry date | Jun 27, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/226
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving a sequence of acoustic frames characterizing one or more utterances as input to a multilingual automated speech recognition (ASR) model. The method also includes generating a higher order feature representation for a corresponding acoustic frame. The method also includes generating a hidden representation based on a sequence of non-blank symbols output by a final softmax layer. The method also includes generating a probability distribution over possible speech recognition hypotheses based on the hidden representation generated by the prediction network at each of the plurality of output steps and the higher order feature representation generated by the encoder at each of the plurality of output steps. The method also includes predicting an end of utterance (EOU) token at an end of each utterance. The method also includes classifying each acoustic frame as either speech, initial silence, intermediate silence, or final silence.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.