Title:
SPEECH SYNTHESIS METHOD AND APPARATUS, AND COMPUTER-READABLE STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2020/200178
Kind Code:
A1
Abstract:
A speech synthesis method, the method comprising: dividing text into a plurality of segments belonging to different language categories (S102); converting each segment into a corresponding phoneme according to the language category to which each segment belongs so as to generate a phoneme sequence of the text ( S104); inputting the phoneme sequence into a pre-trained speech synthesis model and converting same into vocoder feature parameters (S106); and inputting the vocoder feature parameters into a vocoder to generate speech (S108).
Inventors:
WU ZHIZHENG (CN)
ZHANG ZHENGCHEN (CN)
SONG WEI (CN)
RAO YONGHUI (CN)
XIE ZHIHANG (CN)
XU GUANGHUI (CN)
LIU SHUYONG (CN)
MA BOSEN (CN)
QIU SHUANGWEN (CN)
LIN JUNMIN (CN)
ZHANG ZHENGCHEN (CN)
SONG WEI (CN)
RAO YONGHUI (CN)
XIE ZHIHANG (CN)
XU GUANGHUI (CN)
LIU SHUYONG (CN)
MA BOSEN (CN)
QIU SHUANGWEN (CN)
LIN JUNMIN (CN)
Application Number:
PCT/CN2020/082172
Publication Date:
October 08, 2020
Filing Date:
March 30, 2020
Export Citation:
Assignee:
BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO LTD (CN)
BEIJING JINGDONG CENTURY TRADING CO LTD (CN)
BEIJING JINGDONG CENTURY TRADING CO LTD (CN)
International Classes:
G10L13/02
Foreign References:
| CN1540625A | 2004-10-27 | |||
| US20060136216A1 | 2006-06-22 | |||
| TW201705019A | 2017-02-01 | |||
| US9484014B1 | 2016-11-01 | |||
| US20120278081A1 | 2012-11-01 | |||
| CN106297764A | 2017-01-04 |
Other References:
LIUMENG XUE; WEI SONG; GUANGHUI XU; LEI XIE; ZHIZHENG WU: "Building a mixed-lingual neural TTS system with only monolingual data", ELECTRICAL ENGINEERING AND SYSTEMS SCIENCE , 12 April 2019 (2019-04-12), pages 1 - 6, XP081168422
ELIYA NACHMANI; LIOR WOLF: "Unsupervised Polyglot Text To Speech", COMPUTER SCIENCE, 6 February 2019 (2019-02-06), pages 1 - 5, XP081026077
BO LI; YU ZHANG; TARA SAINATH; YONGHUI WU; WILLIAM CHAN: "Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes", ELECTRICAL ENGINEERING AND SYSTEMS SCIENCE, 22 November 2018 (2018-11-22), pages 1 - 5, XP080937763
See also references of EP 3937165A1
ELIYA NACHMANI; LIOR WOLF: "Unsupervised Polyglot Text To Speech", COMPUTER SCIENCE, 6 February 2019 (2019-02-06), pages 1 - 5, XP081026077
BO LI; YU ZHANG; TARA SAINATH; YONGHUI WU; WILLIAM CHAN: "Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes", ELECTRICAL ENGINEERING AND SYSTEMS SCIENCE, 22 November 2018 (2018-11-22), pages 1 - 5, XP080937763
See also references of EP 3937165A1
Attorney, Agent or Firm:
CCPIT PATENT AND TRADEMARK LAW OFFICE (CN)
Download PDF:
Previous Patent: COMMUNICATION METHOD, APPARATUS AND DEVICE, AND STORAGE MEDIUM
Next Patent: HIGHLY ALIGNED AND PACKED HOLLOW FIBER ASSEMBLY
Next Patent: HIGHLY ALIGNED AND PACKED HOLLOW FIBER ASSEMBLY