Title:
PERSONALIZED SPEECH CONVERSION TRAINING METHOD, COMPUTER DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/141126
Kind Code:
A1
Abstract:
Provided is a personalized speech conversion training method, comprising: acquiring a speech parallel corpus of N speakers to train an initial speech conversion model and obtain an speech conversion average model (104); obtaining a speech parallel corpus of a specific speaker and combining with the speech parallel corpus of said N speakers to obtain N sets of training speech data (106); training said speech conversion average model on the basis of the N sets of training speech data to obtain a specific speech conversion average model (108); obtaining first sample speech data of a target speaker and obtaining second sample speech data corresponding to a specific speaker (110), and training the specific speech conversion average model to obtain a target speech conversion model for conversion of specific speech to target speech (112). The invention also relates to a computer device and a storage medium.
Inventors:
HUANG DONGYAN (CN)
WANG RUOTONG (CN)
WANG RUOTONG (CN)
Application Number:
PCT/CN2020/141091
Publication Date:
July 07, 2022
Filing Date:
December 29, 2020
Export Citation:
Assignee:
UBTECH ROBOTICS CORP LTD (CN)
International Classes:
G10L13/04; G10L13/02
Foreign References:
| CN111433847A | 2020-07-17 | |||
| CN109285535A | 2019-01-29 | |||
| CN111613224A | 2020-09-01 | |||
| CN105206257A | 2015-12-30 | |||
| CN105185372A | 2015-12-23 | |||
| CN110033755A | 2019-07-19 | |||
| CN110335588A | 2019-10-15 | |||
| JP2020027168A | 2020-02-20 |
Attorney, Agent or Firm:
SHENZHEN CIPRUN INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: