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

Method and system of transforming speech

A technology of voice conversion and conversion model, which is applied in speech synthesis, speech analysis, speech recognition, etc. It can solve the problems of low voice quality and small amount of training data, and achieve the effect of improving effectiveness, accuracy and effect

Active Publication Date: 2015-11-04
IFLYTEK CO LTD
View PDF7 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitation of application scenarios, the amount of training data that can be obtained is often small, the application model is often relatively simple, and the corresponding converted voice quality is often not high

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 and system of transforming speech
  • Method and system of transforming speech
  • Method and system of transforming speech

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0080] Because the traditional sound conversion system based on spectral transformation mainly uses the GMM model to simulate the probability distribution of the joint spectral feature space of the source speaker and the target speaker, and adopts low-dimensional spectral features, in the process of extracting low-dimensional features from the spectrum A lot of spectral detail information is lost, which directly affects the sound quality of converted speech. Moreover, there is an over-smoothing effect in the GMM model, which leads to an over-smoothing effect in the synthesized speech. To this end, the embodiment of the present invention provides a method and system for realizing sound conversion. Based on the sp...

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 relates to the TTS (Text-To-Speech) technical field, and discloses a method and system of transforming speech. The method comprises: obtaining speech signals of a source speaker; extracting spectrum envelope characteristics and fundamental frequency characteristics of the speech signals; transforming the spectrum envelope characteristics according to a preset spectrum envelope transformation model to obtain transformed spectrum envelope characteristics; and generating speech signals of a target speaker according to the transformed spectrum envelope characteristics and the fundamental frequency characteristics. The method and system can effectively improve the timbre of transformed speech.

Description

technical field [0001] The invention relates to the technical field of voice signal processing, in particular to a method and system for realizing voice conversion. Background technique [0002] Voice conversion is to convert the voice of one speaker (source speaker) into the voice of another speaker (target speaker), so that it has the pronunciation characteristics of the target speaker. Voice conversion technology is widely used in real life. It can help patients implanted with electronic larynx due to damage to their vocal organs to produce high-quality voice. It can also enrich entertainment life and improve entertainment by simulating the pronunciation characteristics of star speakers. It has broad application prospects. [0003] The existing voice conversion system mainly adopts the methods of frequency spectrum conversion and fundamental frequency conversion to convert the voice characteristics of the source speaker so that it has the pronunciation characteristics of...

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): G10L13/02G10L15/02
Inventor 陈凌辉江源凌震华胡国平胡郁刘庆峰
Owner IFLYTEK 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