Systems and methods for accelerating automatic speech recognition based on compression and decompression
US11830480B2 · kind B2 · utility
1Cited by
1References
19Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Feb 17, 2021 |
| Grant date | Nov 28, 2023 |
| Priority date | — |
| Expiry date | Aug 29, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L21/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods are provided for automatic speech recognition. In the method, the system obtains a padded sequence by processing a plurality of acoustic signals. The system compresses the padded sequence by reducing the size of the padded sequence to obtain a compressed sequence. The system inputs the compressed sequence into a pre-trained encoder neural network to obtain an encoded sequence and then decompresses the encoded sequence by recovering the encoded sequence to an original sequential ordering. The system inputs the encoded sequence to a decoding module to obtain recognition texts.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.