Transformer transducer: one model unifying streaming and non-streaming speech recognition
US11741947B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 23, 2021 |
| Grant date | Aug 29, 2023 |
| Priority date | — |
| Expiry date | Nov 11, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A transformer-transducer model for unifying streaming and non-streaming speech recognition includes an audio encoder, a label encoder, and a joint network. The audio encoder receives a sequence of acoustic frames, and generates, at each of a plurality of time steps, a higher order feature representation for a corresponding acoustic frame. The label encoder receives a sequence of non-blank symbols output by a final softmax layer, and generates, at each of the plurality of time steps, a dense representation. The joint network receives the higher order feature representation and the dense representation at each of the plurality of time steps, and generates a probability distribution over possible speech recognition hypothesis. The audio encoder of the model further includes a neural network having an initial stack of transformer layers trained with zero look ahead audio context, and a final stack of transformer layers trained with a variable look ahead audio context.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.