Patent · US Active

Synthetic speech processing

US11017763B1 · kind B1 · utility

5Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 12, 2019
Grant dateMay 25, 2021
Priority date
Expiry dateDec 12, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L13/047
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

During text-to-speech processing, a sequence-to-sequence neural network model may process text data and determine corresponding spectrogram data. A normalizing flow component may then process this spectrogram data to predict corresponding phase data. An inverse Fourier transform may then be performed on the spectrogram and phase data to create an audio waveform that includes speech corresponding to the text.

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