Multi-task training architecture and strategy for attention-based speech recognition system
US11257481B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 24, 2018 |
| Grant date | Feb 22, 2022 |
| Priority date | — |
| Expiry date | Mar 29, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/54
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and apparatuses are provided for performing sequence to sequence (Seq2Seq) speech recognition training performed by at least one processor. The method includes acquiring a training set comprising a plurality of pairs of input data and target data corresponding to the input data, encoding the input data into a sequence of hidden states, performing a connectionist temporal classification (CTC) model training based on the sequence of hidden states, performing an attention model training based on the sequence of hidden states, and decoding the sequence of hidden states to generate target labels by independently performing the CTC model training and the attention model training.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.