Speech recognition with attention-based recurrent neural networks
US9799327B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 26, 2016 |
| Grant date | Oct 24, 2017 |
| Priority date | — |
| Expiry date | Feb 26, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.