Processing acoustic sequences using long short-term memory (LSTM) neural networks that include recurrent projection layers
US9620108B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 2, 2014 |
| Grant date | Apr 11, 2017 |
| Priority date | — |
| Expiry date | Jun 2, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/025
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating phoneme representations of acoustic sequences using projection sequences. One of the methods includes receiving an acoustic sequence, the acoustic sequence representing an utterance, and the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; for each of the plurality of time steps, processing the acoustic feature representation through each of one or more long short-term memory (LSTM) layers; and for each of the plurality of time steps, processing the recurrent projected output generated by the highest LSTM layer for the time step using an output layer to generate a set of scores for the time step.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.