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

Multi-to-multi speaker conversion method based on STARGAN and ResNet

A conversion method and speaker technology, applied in neural learning methods, speech analysis, instruments, etc., can solve problems such as network degradation

Active Publication Date: 2019-07-26
NANJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: the technical problem to be solved in the present invention is to provide a kind of many-to-many speaker conversion method based on STARGAN and ResNet, which solves the problem of existing methods in training The problem of network degradation in the process can reduce the difficulty of semantic learning by the encoding network, improve the spectrum generation quality of the decoding network, and avoid the information loss and noise problems caused by the Batch norm process, and more fully learn semantic features and speakers. Personalized features, so as to better improve the personality similarity and voice quality of the converted voice

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
  • Multi-to-multi speaker conversion method based on STARGAN and ResNet
  • Multi-to-multi speaker conversion method based on STARGAN and ResNet
  • Multi-to-multi speaker conversion method based on STARGAN and ResNet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention builds a ResNet between the encoding network and the decoding network of the generator, which can well solve the problem of network degradation in the training process, further reduce the difficulty of learning the semantics of the encoding network, and improve the spectrum generation quality of the decoding network. Thereby improving the naturalness and fluency of converted speech. Since BN (Batch norm) is the standardization between different samples in a batch, it is important to standardize each batch to ensure that the data distribution is consistent. However, in speech conversion, the generated results mainly depend on a certain speech sample instance, and BN is used to The overall information obtained will not bring any benefits, and the noise it brings will weaken the independence between instances. Therefore, the effect obtained after standardization using BN in the network is not obvious. The naturalness has not been greatly improved, and...

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 multi-to-multi speaker conversion method based on STARGAN and ResNet, which comprises a training stage and a conversion stage, wherein the STARGAN and the ResNet are combinedto achieve a voice conversion system; a ResNet network is utilized to solve the problem of network degradation existing in the STARGAN; the learning capability of semantics and the synthesis capability of a voice spectrum of a model can be better improved; therefore, the individuality similarity and the voice quality of converted voice are better improved; meanwhile, the data is standardized by using the Instant norm; the noise generated in the voice conversion process can be well filtered; the problem of poor voice similarity and natural degree of the converted voice in the STARGAN is solved. A voice conversion method with high quality can be achieved. The method can achieve voice conversion under the condition of non-parallel text, and does not need any alignment process in the trainingprocess, a conversion system with multiple source-target speaker pairs is integrated in a conversion model, namely, the multi-to-multi speaker conversion is achieved.

Description

technical field [0001] The invention relates to a many-to-many speaker conversion method, in particular to a many-to-many speaker conversion method based on STARGAN and ResNet. Background technique [0002] Speech conversion is a research branch in the field of speech signal processing, which is developed and extended on the basis of speech analysis, recognition and synthesis. The goal of voice conversion is to change the voice personality of the source speaker so that it has the voice personality of the target speaker, that is, to make the voice spoken by one person sound like another person's voice after conversion, while preserving semantics information. [0003] After years of research on voice conversion technology, many classic conversion methods have emerged. Most of them include Gaussian Mixed Model (GMM), Recurrent Neural Network (RNN), Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), etc. voice conversion method. However, most of these speech conversi...

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): G10L17/02G10L17/04G10L17/14G10L17/18G10L17/22G10L25/18G06F17/27G06N3/04G06N3/08
CPCG10L17/02G10L17/04G10L17/14G10L17/18G10L17/22G10L25/18G06N3/08G06F40/30G06N3/045
Inventor 李燕萍徐东祥张燕曹盼
Owner NANJING UNIV OF POSTS & TELECOMM
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