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

Voice cloning method and device, training method, electronic equipment and storage medium

A cloning method and voice technology, applied in voice analysis, instruments, etc., can solve problems such as poor imitation ability, weak decoupling ability, high dependence on training data quantity and diversity, and achieve the effect of improving the cloning effect

Pending Publication Date: 2022-04-12
CLOUDMINDS SHANGHAI ROBOTICS CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the inventors of the present invention have found that the voice cloning technology in the prior art has poor imitation ability and poor imitation effect due to the weak decoupling ability of the characteristics of the cloned speaker. Disadvantages of high sexual dependence

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 cloning method and device, training method, electronic equipment and storage medium
  • Voice cloning method and device, training method, electronic equipment and storage medium
  • Voice cloning method and device, training method, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the object, technical solution and advantages of the present invention clearer, various embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, those of ordinary skill in the art can understand that, in each implementation manner of the present invention, many technical details are provided for readers to better understand the present application. However, even without these technical details and various changes and modifications based on the following implementation modes, the technical solution claimed in this application can also be realized.

[0024] The first embodiment of the present invention relates to a voice cloning method, the specific process is as follows figure 1 shown, including:

[0025] Step S101: Encoding the text to be synthesized to obtain the text content features of the text to be synthesized.

[0026] Specifically, in this step, the text to be synthesized is ...

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 field of voice cloning, and discloses a voice cloning method and device, a training method, electronic equipment and a storage medium. The voice cloning method comprises the steps that features of voice to be cloned are decoupled through a first neural network model, speaker features of the voice to be cloned are obtained, the speaker features are features irrelevant to text content in the voice to be cloned, and the first neural network model is a multi-layer neural network model; encoding a to-be-synthesized text to obtain text content features of the to-be-synthesized text; and coupling the speaker features of the to-be-cloned voice and the text content features of the to-be-synthesized text by using a second neural network model to generate a cloned voice. Compared with the prior art, the voice cloning method and device and the model training method of the voice cloning device provided by the embodiment of the invention have the advantages of stronger voice cloning simulation ability and lower dependency on training data volume.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a voice cloning method, device, training method, electronic equipment and storage medium. Background technique [0002] Speech cloning technology is a technology that uses a reference speech signal to synthesize any text, but the speaker characteristics such as timbre, rhythm, style are similar to the target speech signal of the reference speech signal. It can meet the needs of personalized customization of voice or speaking style, and can be used in various mobile assistants, electronic books, smart phone customer service, audio and video dubbing, intelligent interactive robots, etc. Benefiting from the rapid development of deep learning technology, the speech synthesis technology based on neural network has achieved great success. Its synthesized speech is close to the sound quality of real people, and it is difficult to distinguish between true and false. However, with ...

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): G10L17/02G10L17/04G10L17/18G10L19/00
Inventor 李锐
Owner CLOUDMINDS SHANGHAI ROBOTICS 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