Patent · US Active

Waveform generation using end-to-end text-to-waveform system

US11482207B2 · kind B2 · utility

0Cited by
10References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 21, 2020
Grant dateOct 25, 2022
Priority date
Expiry dateDec 21, 2040

Classification

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

Abstract

Described herein are embodiments of an end-to-end text-to-speech (TTS) system with parallel wave generation. In one or more embodiments, a Gaussian inverse autoregressive flow is distilled from an autoregressive WaveNet by minimizing a novel regularized Kullback-Leibler (KL) divergence between their highly-peaked output distributions. Embodiments of the methodology computes the KL divergence in a closed-form, which simplifies the training process and provides very efficient distillation. Embodiments of a novel text-to-wave neural architecture for speech synthesis are also described, which are fully convolutional and enable fast end-to-end training from scratch. These embodiments significantly outperform the previous pipeline that connects a text-to-spectrogram model to a separately trained WaveNet. Also, a parallel waveform synthesizer embodiment conditioned on the hidden representation in an embodiment of this end-to-end model were successfully distilled.

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