Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech synthesis method, device and equipment and computer readable storage medium

A speech synthesis and phoneme technology, applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of low fidelity of synthetic speech and low anthropomorphic degree of synthetic speech, and achieve the effect of improving fidelity and anthropomorphism

Pending Publication Date: 2021-12-24
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although in the speech synthesis process, the naturalness of the synthesized speech can be improved by using contextual text and speech information in the speech synthesis process, or by using a contextual acoustic encoder, however, in the related art, a fixed style is still used to Synthetic speech so that the resulting synthetic speech is less anthropomorphic, resulting in a less realistic synthetic 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
  • Speech synthesis method, device and equipment and computer readable storage medium
  • Speech synthesis method, device and equipment and computer readable storage medium
  • Speech synthesis method, device and equipment and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

preparation example Construction

[0117] see Figure 4 , Figure 4 It is an optional flowchart of the speech synthesis method provided by the embodiment of this application Figure II . In some embodiments of the present application, based on the sentence text, a text feature with a spontaneous behavior label is constructed, that is, the specific implementation process of S102 may include: S1021-S1024, as follows:

[0118] S1021. Perform text feature extraction at the phoneme level on each character information included in the sentence text to obtain text input features of the sentence text.

[0119] The sentence text contains at least one character information, that is, the sentence text is composed of at least one character information. Speech synthesis equipment can use the word segmenter to disassemble the sentence text into individual character information, and then extract text features at the phoneme level for each character information, and use the phoneme-level text features extracted from each cha...

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 invention provides a speech synthesis method, device and equipment and a computer readable storage medium, and relates to a speech technology in the field of artificial intelligence. The method comprises the steps: obtaining a statement text, wherein the statement text records dialogue content waiting for speech synthesis at the current moment; based on the statement text, constructing text features with a spontaneous behavior tag, wherein the spontaneous behavior tag indicates the occurrence position and type of the spontaneous acoustic behavior in the dialogue content; performing feature conversion on the text features to obtain acoustic features corresponding to the statement text; and generating a synthetic speech with a spontaneous acoustic behavior corresponding to the statement text by using the acoustic features. According to the invention, the vivid degree of the synthetic speech can be improved.

Description

technical field [0001] The present application relates to speech technology in the field of artificial intelligence, and in particular to a speech synthesis method, device, equipment and computer-readable storage medium. Background technique [0002] Speech synthesis technology is a technology for generating artificial voice, which can be applied in intelligent customer service, robots and other fields. Although in the speech synthesis process, the naturalness of the synthesized speech can be improved by using contextual text and speech information in the speech synthesis process, or by using a contextual acoustic encoder, however, in the related art, a fixed style is still used to Synthetic speech so that the resulting synthetic speech is less anthropomorphic, ultimately resulting in a less realistic synthetic speech. Contents of the invention [0003] Embodiments of the present application provide a speech synthesis method, device, device, and computer-readable storage ...

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
CPCG10L13/02G10L13/08G10L13/04
Inventor 阳珊胡娜李广之苏丹
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com