Title:
SPEECH WAVEFORM GENERATION
Document Type and Number:
WIPO Patent Application WO/2020/062217
Kind Code:
A1
Abstract:
A method and apparatus for generating a speech waveform. Fundamental frequency information, glottal features and vocal tract features associated with an input may be received, wherein the glottal features include a phase feature, a shape feature, and an energy feature (1310). A glottal waveform is generated based on the fundamental frequency information and the glottal features through a first neural network model (1320). A speech waveform is generated based on the glottal waveform and the vocal tract features through a second neural network model (1330).
Inventors:
CUI YANG (US)
WANG XI (US)
HE LEI (US)
SOONG KAO-PING (US)
WANG XI (US)
HE LEI (US)
SOONG KAO-PING (US)
Application Number:
PCT/CN2018/109044
Publication Date:
April 02, 2020
Filing Date:
September 30, 2018
Export Citation:
Assignee:
MICROSOFT TECHNOLOGY LICENSING LLC (US)
CUI YANG (CN)
WANG XI (CN)
HE LEI (CN)
SOONG KAO PING (CN)
CUI YANG (CN)
WANG XI (CN)
HE LEI (CN)
SOONG KAO PING (CN)
International Classes:
G10L13/00
Domestic Patent References:
WO2010031437A1 | 2010-03-25 | |||
WO2009055701A1 | 2009-04-30 |
Foreign References:
CN102047321A | 2011-05-04 | |||
CN107221317A | 2017-09-29 | |||
CN108369803A | 2018-08-03 | |||
US20030088417A1 | 2003-05-08 | |||
CN102047321A | 2011-05-04 |
Other References:
See also references of EP 3857541A4
Attorney, Agent or Firm:
NTD PATENT & TRADEMARK AGENCY LTD. (CN)
Download PDF: