Patent · US Active

Text-to-speech (TTS) processing

US11410639B2 · kind B2 · utility

3Cited by
1References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 7, 2020
Grant dateAug 9, 2022
Priority date
Expiry dateJul 30, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L13/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

During text-to-speech processing, a speech model creates output audio data, including speech, that corresponds to input text data that includes a representation of the speech. A spectrogram estimator estimates a frequency spectrogram of the speech; the corresponding frequency-spectrogram data is used to condition the speech model. A plurality of acoustic features corresponding to different segments of the input text data, such as phonemes, syllable-level features, and/or word-level features, may be separately encoded into context vectors; the spectrogram estimator uses these separate context vectors to create the frequency spectrogram.

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