Patent · US Active

Speech style transfer

US11538455B2 · kind B2 · utility

3Cited by

3References

27Claims

0Family size

Assignee

Dolby Laboratories Licensing Corporation · US

Inventors

Cong Zhou · Nanhu, CN
Michael Getty HORGAN · San Francisco, US
Vivek Kumar · Foster City, US
Jaime H. Morales · Alameda, US
Cristina Michel Vasco · San Francisco, US

Key dates

Filing date	Feb 14, 2019
Grant date	Dec 27, 2022
Priority date	—
Expiry date	Dec 22, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG10L25/30
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Computer-implemented methods for speech synthesis are provided. A speech synthesizer may be trained to generate synthesized audio data that corresponds to words uttered by a source speaker according to speech characteristics of a target speaker. The speech synthesizer may be trained by time-stamped phoneme sequences, pitch contour data and speaker identification data. The speech synthesizer may include a voice modeling neural network and a conditioning neural network.

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