Patent · US Active

Apparatus and method for speech processing using a densely connected hybrid neural network

US11837220B2 · kind B2 · utility

0Cited by
2References
18Claims
0Family size

Assignees

Inventors

Key dates

Filing dateMay 5, 2021
Grant dateDec 5, 2023
Priority date
Expiry dateFeb 18, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L21/0208
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed is a speech processing apparatus and method using a densely connected hybrid neural network. The speech processing method includes inputting a time domain sample of N*1 dimension for an input speech into a densely connected hybrid network; passing the time domain sample through a plurality of dense blocks in a densely connected hybrid network; reshaping the time domain samples into M subframes by passing the time domain samples through the plurality of dense blocks; inputting the M subframes into gated recurrent unit (GRU) components of N/M-dimension; outputting clean speech from which noise is removed from the input speech by passing the M subframes through GRU components.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.