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

Sound imitation method and device

A sound and channel technology, applied in the field of sound imitation methods and devices, can solve the problems of unsatisfactory sound simulation effect, low similarity of sound simulation, single sound material library data, etc. Imitation of high similarity and overcoming the effect of single data

Active Publication Date: 2016-06-15
HUNAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To sum up, the current sound simulation methods generally have problems such as unsatisfactory sound simulation effects, low similarity of sound simulation, single data in the sound library, unable to grow, and cannot be changed.

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
  • Sound imitation method and device
  • Sound imitation method and device
  • Sound imitation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] Such as figure 1 and figure 2 As shown, the implementation steps of the sound imitation method of the present embodiment are as follows:

[0079] 1) Obtain the speaker's voice signal and the imitation object specified in the sound material library, preprocess the voice signal by frame and window, select a voice frame from the preprocessed voice signal as the current voice frame, and jump to execute Step 2).

[0080] When collecting voice signals in this embodiment, it is specifically to collect them through hardware devices with recording, playback functions and mobile network services. is k, the frame shift is k', the number of frames is N, the voice data of the nth frame is s(n), and the corresponding synthetic frame obtained by simulation is S(n).

[0081] Such as image 3 As shown, in the present embodiment, after the voice signal is subjected to framed and windowed preprocessing, the step of storing the voice signal as an imitation object in the sound material...

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 sound imitation method and device. The method steps include acquiring a speech signal and an imitation object, preprocessing the speech signal, performing pitch conversion and timbre conversion on each speech frame of the speech signal according to the imitation object, and resynthesizing to obtain a synthesis. voice frame, adding the synthesized voice frame to the simulated voice frame, and finally outputting the simulated voice composed of the simulated voice frame. The sound imitation device includes an input module, a tone conversion module, a timbre conversion module, a speech frame synthesis module, an imitation speech frame addition module, a judgment processing module and an imitation speech output module. The invention has the advantages of good sound imitation effect, high sound imitation similarity and automatic extension of the sound material library.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a sound imitation method and device. Background technique [0002] With the rapid development of speech signal processing technology and the popularity of social platforms, research on voice imitation highlights its application advantages and gradually occupies an important position. The common voice imitation methods in the prior art all change the vocal tract model, the effect of the voice imitation is not ideal, and there is a shortcoming of low similarity of the voice simulation. [0003] The technical solution disclosed in the Chinese invention patent application with the publication number CN102592590A records a method and device for arbitrarily adjustable speech natural voice change. model, and then change the channel model, and finally restore the speech signal in the new channel model. To a certain extent, the timbre change of the sound has been realized, but th...

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): G10L13/02G10L19/04
Inventor 赵欢郑睿陈佐张希翔杨泽英
Owner HUNAN UNIV
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