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

Method, device and electronic equipment for speech synthesis

A technology of speech synthesis and synthetic speech, which is applied in speech synthesis, speech analysis, instruments, etc., and can solve problems such as inconsistency in timbre

Active Publication Date: 2020-12-11
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a speech synthesis method, device and electronic equipment, which are used to solve the technical problem of inconsistency in timbre in parametric speech synthesis in the prior art

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
  • Method, device and electronic equipment for speech synthesis
  • Method, device and electronic equipment for speech synthesis
  • Method, device and electronic equipment for speech synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0081] Please refer to figure 1 , the embodiment of the present application provides a method of speech synthesis, the method comprising:

[0082] S101: extract the fundamental frequency parameter and the amplitude parameter of the fixed component text audio from the recording of the fixed component text;

[0083] S102: Perform audio compression and filtering processing according to the amplitude parameter to obtain spectral parameters of the fixed-component text audio;

[0084] S103: When synthesizing speech, synthesize speech based on the fundamental frequency parameters and spectrum parameters of the fixed component text in the speech to be synthesized.

[0085] In the specific implementation process, the embodiment of the present application can establish a template library before synthesizing speech, and store the fundamental frequency parameters and spectrum parameters of the fixed component text. When building a template library, record commonly used texts and extract...

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 discloses a voice synthesis method and device and electronic equipment. The method comprises the steps: extracting the fundamental frequency parameter and amplitude parameter of a fixedcomponent text audio from the record of a fixed component text; carrying out the audio limiting and filtering according to the amplitude parameter, and obtaining the spectrum parameters of the fixed component text audio; and synthesizing the voice based on the fundamental frequency parameter and amplitude parameter of the fixed component text in a to-be-synthesized voice during voice synthesis. According to the technical scheme, the method enables the amplitude of the audio to be more balanced and the audio to be coordinative and consistent through the audio limiting and filtering, enables thespectrum parameters to be consistent with the tone of a pure-parameter synthesized voice (a non-fixed component text), and achieves the synthesis of the voice based on the fundamental frequency parameter and amplitude parameter of the fixed component text audio. The tone of the fixed component text and the tone of the non-fixed component text are consistent with each other, thereby solving a technical problem that the parameter voice synthesis tones are not consistent in the prior art.

Description

technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a speech synthesis method, device and electronic equipment. Background technique [0002] Parametric speech synthesis is currently a mainstream speech synthesis technology. Parametric speech synthesis takes up less space and has high real-time computing performance. It has broad application prospects in smart terminals and embedded devices. [0003] Parametric speech is completed by synthetic text, which is usually composed of fixed components (ie, fixed component text) and variable parameter components (ie, non-fixed component text). In the prior art, during speech synthesis, the fixed component text is pre-recorded natural speech to obtain part of the speech segment, and the variable component text is subjected to speech synthesis to obtain another speech segment, and then the two speech segment signals are spliced ​​to obtain the final continuous speech sign...

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 Patents(China)
IPC IPC(8): G10L13/04G10L13/08
CPCG10L13/04G10L13/08
Inventor 宋阳
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT 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