Construction method and device for speech synthesis model and construction device for speech synthesis model

A speech synthesis and model technology, applied in the field of input methods, can solve problems such as inaccurate pronunciation, small amount of speech data, and wrong pronunciation of speech, and achieve the effects of improving pronunciation accuracy, improving efficiency, and reducing costs

Pending Publication Date: 2021-11-26
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the amount of speech data of a single speaker is small, and it is difficult to cover all the pronunciation, which will lead to mispronunciation or inaccurate pronunciation of the synthesized speech

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Construction method and device for speech synthesis model and construction device for speech synthesis model
  • Construction method and device for speech synthesis model and construction device for speech synthesis model
  • Construction method and device for speech synthesis model and construction device for speech synthesis model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0069] method embodiment

[0070] refer to figure 1 , which shows a flow chart of the steps of an embodiment of a method for constructing a speech synthesis model of the present invention, the method may specifically include the following steps:

[0071] Step 101, selecting a data subset with complete phoneme coverage from the multi-person voice data;

[0072] Step 102, using the mixed data composed of the individual speech data of the target speaker...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention provides a construction method and device for a speech synthesis model and a construction device for the speech synthesis model. The method comprises the following steps: selecting a data subset with complete phoneme coverage from multi-person voice data; and taking mixed data composed of single-person voice data of a target speaker and the data subset as training data, and performing adaptive training on a multi-person voice synthesis model by using the training data to obtain a single-person voice synthesis model of the target speaker. According to the embodiment of the invention, the problem of incomplete phoneme coverage of the single-person speech data of the target speaker can be solved, and the pronunciation accuracy of the single-person speech synthesis model of the target speaker obtained by final training can be improved.

Description

technical field [0001] The invention relates to the technical field of input methods, in particular to a method and device for constructing a speech synthesis model and a construction device for the speech synthesis model. Background technique [0002] With the development of deep learning, speech synthesis technology has entered the end-to-end development stage. The end-to-end speech synthesis model can directly output the speech corresponding to the text based on the input text. Speech synthesis technology is widely used in scenarios such as intelligent question answering and voice broadcasting. [0003] At present, it is possible to use a large number of speakers' voice data to train the speech synthesis model, and then use the speech data of a single speaker for adaptive training on the basis of the trained speech synthesis model to obtain the speech synthesis model of the target speaker's timbre. [0004] However, the amount of speech data of a single speaker is small...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L13/02G10L13/04G10L13/08
CPCG10L13/02G10L13/04G10L13/08
Inventor 王睿敏孟凡博刘恺王砚峰
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap