Voice conversion method based on adaptive Gaussian clustering under non-parallel text condition

A speech conversion, non-parallel technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of weak personality information of the speaker

Active Publication Date: 2017-10-27
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can make reasonable use of pre-stored speaker information, but usually the adaptive process w

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
  • Voice conversion method based on adaptive Gaussian clustering under non-parallel text condition
  • Voice conversion method based on adaptive Gaussian clustering under non-parallel text condition
  • Voice conversion method based on adaptive Gaussian clustering under non-parallel text condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0073] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in commonly used dictionaries should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless defined as herein Explanation.

[0074] The high-quality speech conversion method of the present invention is divided into two parts: the training part is used to obtain the parameters and conversion functions required for speech conversion, and the conversion part is used to realize the conversion of the source speaker's voice ...

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 conversion method based on adaptive Gaussian clustering under a non-parallel text condition, and belongs to the technical field of voice signal processing. The method comprises the steps: firstly carrying out the voice feature parameter alignment of non-parallel linguistic data through a method based on the combination of unit selection and sound channel length normalization; secondly carrying out the training of an adaptive Gaussian mixed model and bilinear frequency bending and amplitude adjustment, and obtaining a conversion function needed by voice conversion; finally achieving the high-quality voice conversion through the conversion function. The method overcomes the limit that the training stage requires the parallel linguistic data, achieves the voice conversion under the non-parallel text condition, is higher in adaptability and universality, employs the adaptive Gaussian mixed model to replace a conventional Gaussian mixed model, solves a problem that a Gaussian mixed model is not precise in voice feature parameter classification, combines the adaptive Gaussian mixed model with the bilinear frequency bending and amplitude adjustment, and is better in conversion personality similarity and voice quality.

Description

technical field [0001] The invention relates to a voice conversion technology, in particular to a voice conversion method under the condition of non-parallel text, and belongs to the technical field of voice signal processing. Background technique [0002] Speech conversion is an emerging research branch in the field of speech signal processing in recent years. It is carried out and developed on the basis of speech analysis, recognition and synthesis. [0003] The goal of voice conversion is to change the voice personality of the source speaker so that it has the voice personality of the target speaker, that is, to make the voice spoken by one person sound like another person's voice after conversion, while preserving semantics . [0004] Most speech conversion methods, especially those based on GMM, require the corpus used for training to be parallel text, that is, the source speaker and the target speaker need to utter sentences with the same speech content and speech dur...

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): G10L15/02G10L15/06G10L15/07G10L15/14G10L17/02G10L21/007G10L25/51G10L19/032
CPCG10L15/02G10L15/063G10L15/07G10L15/14G10L17/02G10L19/032G10L21/007G10L25/51
Inventor 李燕萍左宇涛
Owner NANJING UNIV OF POSTS & TELECOMM
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