Unlock instant, AI-driven research and patent intelligence for your innovation.

A voice conversion system and method

A speech conversion, speech technology, applied in speech analysis, speech recognition, speech synthesis and other directions, can solve the problem of inability to achieve transformation

Active Publication Date: 2017-11-07
吉林科讯信息科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the technologies provided by these two patents can only convert text into sound, and cannot realize the transformation from one speaker to another.

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
  • A voice conversion system and method
  • A voice conversion system and method
  • A voice conversion system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The specific content of the present invention will be described below in conjunction with the accompanying drawings.

[0029] The system of the present invention is divided into two modes: training mode and conversion mode. The training mode can be used to build a specific person's speech feature library; the conversion mode can convert the voice of speaker A into the voice of specific person B.

[0030] The system described in the present invention has five parts in all:

[0031] Recording module: used to receive the speaker's voice, and send the recording to the recognition module for feature extraction and semantic recognition.

[0032] Speech recognition module: Receive the recording of the recording module, in the training mode, extract the feature information of the recording and send it to the synthesis module for building the feature library; in the conversion mode, perform semantic recognition on the voice, and output the recognized text.

[0033] Speech synt...

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

A speech conversion system and method, comprising: a recording module, a speech recognition module, a speech synthesis module, a loudspeaker module and a user control module; the recording module is connected with the speech recognition module, receives the speaking voice of a speaker and records the audio; The speech recognition module performs speech recognition according to different modes, and extracts relevant speech feature information during the training mode; converts the speech signal into corresponding text information in the conversion mode; the speech synthesis module receives the speech features transmitted from the speech recognition mode during the training mode The information is stored, and when the mode is converted, the received text information is combined with the voice feature information of a specific person to synthesize, and the synthesized voice is sent to the speaker module; the user control module controls the startup and shutdown of the system, and can select the working mode, It is also possible to select a designated person to synthesize, that is, whose voice the voice is to be converted into.

Description

technical field [0001] The invention relates to the technical fields of voice recognition technology and personalized voice synthesis, which can convert the words spoken by a speaker A into the voice of a specific person B and then play them. Background technique [0002] Speech recognition technology is a technology that converts the speaker's voice into text. Personalized speech synthesis technology is developed on the basis of speech synthesis technology TTS. In addition to the traditional TTS conversion of text into speech broadcast, it can also be synthesized into a speech with specific person characteristics, but it needs to obtain the designated person first. Speech audio, extract the speech features of specific people from the audio, and build a personalized speech feature library. Such as the patent "Accepting the text input by the user on the mobile phone or the webpage and synthesizing it into a personalized voice method" (public number: CN103065620A) proposed by...

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): G10L15/02G10L13/02
Inventor 梅珂刘俊峰陈盛
Owner 吉林科讯信息科技有限公司