Patent · US Active

Processing acoustic sequences using long short-term memory (LSTM) neural networks that include recurrent projection layers

US9620108B2 · kind B2 · utility

20Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 2, 2014
Grant dateApr 11, 2017
Priority date
Expiry dateJun 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.