End-to-end automatic speech recognition with transformer
US12380880B2 · kind B2 · utility
0Cited by
2References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 3, 2023 |
| Grant date | Aug 5, 2025 |
| Priority date | — |
| Expiry date | Feb 7, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0633
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An end-to-end automatic speech recognition (ASR) system can be constructed by fusing a first ASR model with a transformer. The input of the transformer is a learned layer generated by the first ASR model. The fused ASR model and transformer can be treated as a single end-to-end model and trained as a single model. In some embodiments, the end-to-end speech recognition system can be trained using a teacher-student training technique by selectively truncating portions of the first ASR model and/or the transformer components and selectively freezing various layers during the training passes.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.