Title:
SINGING SYNTHESIS METHOD AND APPARATUS, AND COMPUTER DEVICE AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/169491
Kind Code:
A1
Abstract:
A singing synthesis method and apparatus, and a computer device and a storage medium. The method comprises: acquiring voice data (S10); parsing the voice data to obtain a spectral envelope, an aperiodic index, a fundamental frequency contour and a phoneme (S20); synthesizing music bar information in a music score and the fundamental frequency contour to obtain a first fundamental frequency contour (S40); carrying out fundamental frequency control processing on the fundamental frequency contour to obtain a second fundamental frequency contour (S50); synthesizing the first fundamental frequency contour and the second fundamental frequency contour to obtain a target fundamental frequency contour (S60); carrying out spectrum control processing on the spectral envelope and the aperiodic index to obtain a target spectral envelope and a target aperiodic index (S70); carrying out speed change processing on the phoneme to obtain a target phoneme (S80); synthesizing the target spectral envelope, the target aperiodic index, the target phoneme and the target fundamental frequency contour to obtain target voice data (S90); and carrying out spectrum control processing on the target voice data to obtain target singing data (S100). By means of the method, synthesized target singing data is more consistent with sound made by a user, such that the singing synthesis effect is better.
Inventors:
ZHU QINGYING (CN)
WANG JIANZONG (CN)
WANG JIANZONG (CN)
Application Number:
PCT/CN2020/135725
Publication Date:
September 02, 2021
Filing Date:
December 11, 2020
Export Citation:
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G10L13/04; G10L13/047
Foreign References:
| CN111402858A | 2020-07-10 | |||
| CN110148394A | 2019-08-20 | |||
| CN109817197A | 2019-05-28 | |||
| CN110741430A | 2020-01-31 | |||
| CN108461079A | 2018-08-28 | |||
| CN104766602A | 2015-07-08 | |||
| US20150310850A1 | 2015-10-29 |
Other References:
SAITOU TAKESHI, GOTO MASATAKA, UNOKI MASASHI, AKAGI MASATO: "Speech-to-Singing Synthesis System: Vocal Conversion from Speaking Voices to Singing Voices by Controlling Acoustic Features Unique to Singing Voices", NCMMSC2009, 16 August 2009 (2009-08-16), XP055841867, Retrieved from the Internet
TAKESHI SAITOU ; MASATAKA GOTO ; MASASHI UNOKI ; MASATO AKAGI: "Speech-to-Singing Synthesis: Converting Speaking Voices to Singing Voices by Controlling Acoustic Features Unique to Singing Voices", APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS, 2007 IEEE WO RKSHOP ON, IEEE, PI, 1 October 2007 (2007-10-01), Pi, pages 215 - 218, XP031167096, ISBN: 978-1-4244-1618-9
TAKESHI SAITOU ; MASATAKA GOTO ; MASASHI UNOKI ; MASATO AKAGI: "Speech-to-Singing Synthesis: Converting Speaking Voices to Singing Voices by Controlling Acoustic Features Unique to Singing Voices", APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS, 2007 IEEE WO RKSHOP ON, IEEE, PI, 1 October 2007 (2007-10-01), Pi, pages 215 - 218, XP031167096, ISBN: 978-1-4244-1618-9
Attorney, Agent or Firm:
SHENZHEN ZHONGDING INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF: