User tone based method and device for voice synthesis

A speech synthesis and user technology, applied in speech synthesis, speech analysis, speech recognition, etc., can solve the problem of not being able to change the timbre of the machine independently, and achieve the effect of convenient, fast and accurate recording, improved quality, and accurate timbre characteristics.

Active Publication Date: 2018-11-20
BEIJING UNISOUND INFORMATION TECH
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a method and device for speech synthesis based on the user's timbre to solve the defect that the user cannot independently change the timbre of the machine's voice

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
  • User tone based method and device for voice synthesis
  • User tone based method and device for voice synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0048] The embodiment of the present invention provides a method for performing speech synthesis based on the user's timbre, which is executed by a local terminal. The local terminal may specifically be a smart phone, a tablet computer, a handheld computer, a PC, etc. APP (application program), WeChat applet, or other carrier implementation, which is not limited in this embodiment. see figure 1 As shown, the method includes steps 101-106:

[0049] Step 101: Obtain user audio data input by the user, and determine user timbre characteristics of the user audio data.

[0050] In the embodiment of the present invention, when the user needs to adjust the timbre of the d...

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 user tone based method and device for voice synthesis. The method includes acquiring user audio data input by a user and determining user tone features of user audio data; synthesizing testing audio data corresponding to testing data according to the user tone features and the testing data and broadcasting and receiving a broadcasting adjustment command of the user for thetesting audio data; modifying the user tone features according to the broadcasting adjustment command and taking the modified user tone features as the final standard tone features; synthesizing target audio data corresponding to to-be-broadcasted data according to the standard tone features and the to-be-broadcasted data. According to the invention, the tone features of the user are extracted and the audio data is broadcasted based on tone features of the user, so that user sounding can be simulated and audio broadcasting truth can be improved. The tone features can be adjusted based on thebroadcasting adjusting command of the user, so that the finally broadcasted audio data can be more in line with features and demands of the user.

Description

technical field [0001] The invention relates to the technical field of voice processing, in particular to a method and device for voice synthesis based on user timbre. Background technique [0002] With the popularization of smart devices, most smart devices (such as smart phones, robots, etc.) currently have an automatic pronunciation function. But at present, most smart devices just emit machine sounds. For smart devices that require human-computer interaction through voice, machine sounds are relatively monotonous and boring. They do not sound as vivid as natural language, and are too blunt to reflect the user himself. features. However, existing smart devices do not support users to change the timbre of the machine's voice independently. Contents of the invention [0003] The invention provides a method and device for speech synthesis based on the user's timbre to solve the defect that the user cannot independently change the timbre of the machine's voice. [0004] ...

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): G10L13/08G10L13/10G10L15/14G10L17/02G10L21/0208
CPCG10L13/08G10L13/10G10L15/142G10L17/02G10L21/0208G10L2021/02087
Inventor 吴千瑜
Owner BEIJING UNISOUND INFORMATION TECH
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