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

Real-time voice changing method and device

A technology of sound-changing and acoustic characteristics, applied in the field of real-time sound-changing methods and devices, can solve problems such as inability to meet real-time requirements and poor sound-changing effects, and achieve the effects of meeting application requirements, low response delay, and good sound-changing effects.

Pending Publication Date: 2020-08-07
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The voice changing effect obtained by using this voice changing processing method is not good, and it cannot meet some application scenarios with real-time requirements

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
  • Real-time voice changing method and device
  • Real-time voice changing method and device
  • Real-time voice changing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056]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.

[0057] Embodiments of the present invention provide a real-time voice changing method and device, which pre-constructs a timbre conversion model corresponding to a specific target speaker, extracts speech recognition acoustic features from the received source speaker audio data, and uses the speech recognition acoustic features to obtain speech recognition Hidden layer features, using the hidden layer features as an intermediary, using the timbre conversion model to convert the speech recognition acoustic features corresponding to the source speaker into the speech synthesis acoustic features corresponding to a specific target speaker, and then using the speech synthesis acoustic features Generate a target speaker...

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 real-time voice changing method and device. The method comprises the following steps: receiving audio data of a source speaker; extracting voice recognition acoustic featuresfrom the source speaker audio data, and obtaining hidden layer features of voice recognition by using the voice recognition acoustic features; inputting the hidden layer features into a pre-constructed tone conversion model corresponding to a specific target speaker to obtain speech synthesis acoustic features of the specific target speaker; and generating an audio signal of the specific target speaker by using the speech synthesis acoustic feature of the specific target speaker. According to the invention, real-time sound changing with low response delay can be realized, and a good sound changing effect can be obtained.

Description

technical field [0001] The invention relates to the field of voice signal processing, in particular to a real-time voice changing method and device. Background technique [0002] At present, with the development of speech synthesis technology, how to make the synthesized speech natural, diverse, and personalized has become a hot topic in speech technology research, and voice-changing technology is one of the ways to diversify and personalize the synthesized speech. Voice-changing technology mainly refers to the technology that retains the semantic content of the speech signal but changes the characteristics of the speaker's voice, making someone's voice sound like another person's voice. From the perspective of speaker conversion, voice changing technology is usually divided into two ways: one is the voice conversion between non-specific people, such as the conversion between male and female voices, and the conversion between different age levels; the other is Speech conver...

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): G10L21/013G10L15/02G10L17/04G10L13/08G10L25/12G10L25/18G10L25/24G10L25/30G10L25/93
CPCG10L13/08G10L15/02G10L17/04G10L21/013G10L25/12G10L25/18G10L25/24G10L25/30G10L25/93G10L2021/0135
Inventor 刘恺
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT 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