Two-pass end to end speech recognition
US12073824B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 3, 2020 |
| Grant date | Aug 27, 2024 |
| Priority date | — |
| Expiry date | Oct 20, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0635
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Two-pass automatic speech recognition (ASR) models can be used to perform streaming on-device ASR to generate a text representation of an utterance captured in audio data. Various implementations include a first-pass portion of the ASR model used to generate streaming candidate recognition(s) of an utterance captured in audio data. For example, the first-pass portion can include a recurrent neural network transformer (RNN-T) decoder. Various implementations include a second-pass portion of the ASR model used to revise the streaming candidate recognition(s) of the utterance and generate a text representation of the utterance. For example, the second-pass portion can include a listen attend spell (LAS) decoder. Various implementations include a shared encoder shared between the RNN-T decoder and the LAS decoder.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.