Sound conversion optimization method and system

A technology of sound conversion and optimization method, applied in speech analysis, instruments, etc., can solve the problems of distortion of conversion quality and unnatural sound, and achieve the effect of simplifying structure and calculation

Active Publication Date: 2018-11-20
AISPEECH CO LTD
View PDF10 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the process of realizing the present invention, the inventor finds that the sound of the last synthesis is unnatural, and an important factor is that the acoustic features used for parametric speech con

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 conversion optimization method and system
  • Sound conversion optimization method and system
  • Sound conversion optimization method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. 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.

[0028] In the following, the embodiment of the present application will be introduced first, and then the experimental data will be used to verify the difference between the solution of the present application and the prior art, and what beneficial effects can be achieved.

[0029] Please refer to figure 1 , which shows a flow chart of an embodim...

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 conversion optimization method and system. The method comprises steps that original Mel-spectrum features are extracted from an original audio signal; the original Mel-spectrum features are mapped through frame-to-frame features to obtain target Mel-spectrum features; the original audio signal is taken as input, the target Mel-spectrum features are taken as the condition, and the original audio signal is inputted to a sound conversion vocoder to obtain an optimized audio signal. The method is advantaged in that the high quality audio conversion structure is proposed, a Mel cepstral coefficient and the fundamental frequency F0 commonly used in acoustic features are discarded, instead, a very low level of the Mel spectrum is used as an acoustic feature, the sound is more natural compared with the sound converted in the prior art while the structure and calculation are simplified.

Description

technical field [0001] The invention belongs to the technical field of sound conversion, in particular to a sound conversion optimization method and system. Background technique [0002] Voice Conversion (VC) is a technique used to modify the speech of a source speaker to sound like the target speaker while preserving the linguistic content. Traditional voice transformation techniques focus on developing transformation functions using some parallel data of source and target speakers speaking the same sentences. Some transformation models, such as Gaussian mixture model (GMM), deep neural network have been applied to transform the acoustic features of the source speaker to the corresponding target speaker. [0003] The sound quality of converted speech is always attractive to researchers. The converted speech in the related art always suffers from distortion, for example, excessive smoothing, lack of similarity, and the like. In parametric sound transformation, several tec...

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
IPC IPC(8): G10L21/003G10L21/007G10L21/013G10L25/24
CPCG10L21/003G10L21/007G10L21/013G10L25/24G10L2021/0135
Inventor 俞凯陈宽陈博
Owner AISPEECH 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