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

Voice filtering method and device, electronic equipment and storage medium

A filtering method and voice technology, applied in the fields of devices, electronic equipment and storage media, and voice filtering methods, can solve problems such as poor voice conversion effect, and achieve the effect of improving the effect.

Pending Publication Date: 2022-04-08
成都爱奇艺智能创新科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present application provides a voice filtering method, device, electronic equipment and storage medium to solve the problem in the related art that the prosody vector contains redundant information, resulting in poor voice conversion effect during voice conversion

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 filtering method and device, electronic equipment and storage medium
  • Voice filtering method and device, electronic equipment and storage medium
  • Voice filtering method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, but not all of them. Based on the embodiments in the present application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present application.

[0031] figure 1 A schematic flow diagram of a voice filtering method provided in the embodiment of the present application, such as figure 1 As shown, the voice filtering method includes:

[0032] S101. Perform an alignment operation on the prosodic vectors of the target speech according to the speech alignment sequence to obtain mult...

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 a voice filtering method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the alignment operation of a rhythm vector of a target voice according to a voice alignment sequence, so as to obtain a plurality of groups of alignment vectors, and enabling the voice alignment sequence to be a sequence obtained by carrying out the phoneme division of the target voice; obtaining a hidden state of each group of alignment vectors, and carrying out downsampling on the hidden state to obtain a downsampling vector; and reconstructing the downsampling vector to obtain a filtering rhythm vector consistent with the rhythm vector in length, the filtering rhythm vector being used for performing voice conversion on the target voice. According to the method, the voice alignment sequence is introduced to align the rhythm vector, and meanwhile, hidden information carrying a plurality of vectors is used for reconstruction to obtain the filtered rhythm vector, so that the defect of selection for reconstruction by a random vector is overcome, and enough rhythm information is reserved while the rhythm vector of the target voice is filtered.

Description

technical field [0001] The present application relates to the technical field of voice conversion, and in particular to a voice filtering method, device, electronic equipment and storage medium. Background technique [0002] With the continuous development of deep learning technology, neural network-based voice conversion (Voice Conversion, VC) technology is also becoming more and more mature. Speech conversion refers to changing the acoustic feature parameters related to the personality characteristics of the source speaker to make it sound like the voice of the target speaker without changing the semantics. However, there is an important defect in the current voice conversion technology , the expressive power of the original voice cannot be preserved, but the expressive power is particularly important in voice conversion technology. In the related technology, in the speech conversion technology, the mel spectrum of the original speech is directly used as a prosody module ...

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): G10L25/24G10L25/87G10L15/14G10L15/16G10L13/033
Inventor 甘文东文博龙闫影陈海涛郭凯旋李海黄心驰
Owner 成都爱奇艺智能创新科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More