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

Many-to-many voice conversion method based on beta-VAE

A voice conversion, many-to-many technology, applied in the direction of voice analysis, instruments, etc., can solve the problems of insufficient representation ability, difficult to expand, etc., achieve high-quality voice conversion, improve voice quality, and relieve dependence

Active Publication Date: 2019-07-23
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: the technical problem to be solved by the present invention is to provide a beta-VAE-based many-to-many voice conversion method, which solves the problem that the hidden variables in the existing VAE network have insufficient characterization capabilities for voice data and are difficult to expand to more complex Insufficient voice data, better improve the voice quality after conversion, and effectively improve the conversion performance

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
  • Many-to-many voice conversion method based on beta-VAE
  • Many-to-many voice conversion method based on beta-VAE
  • Many-to-many voice conversion method based on beta-VAE

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Such as figure 1 As shown, the present embodiment provides a many-to-many voice conversion method based on beta-VAE under a non-parallel text condition, which is divided into two steps of training and conversion:

[0032] 1. Speaker voice training stage

[0033] 1.1 Obtain non-parallel training corpus. The speech library used here is VCC2018, which contains 8 source speakers (SF1, SF2, SM1, SM2, SF3, SF4, SM3, SM4) and 4 target speakers (TF1 , TF2, TM1, TM2). The non-parallel training corpus selected in this paper is 4 source speakers: SF3, SF4, SM3, SM4, and 4 target speakers TF1, TF2, TM1, TM2. Among them, S (source) represents the source speaker, T (target) represents the target speaker, F (female) represents female, and M (male) represents male. Since the goal of this paper is non-parallel speech conversion, the selected training corpus is also non-parallel. There are 4 source speakers: SF3, SF4, SM3, SM4, and 4 target speakers TF1, TF2, TM1, TM2. The content of...

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 many-to-many voice conversion method based on a beta-VAE. By introducing adjustable parameters beta and C, a variational automatic encoder frame is modified, the disentanglement capacity of a hidden variable is improved, the problem that the encoding capacity of the variational automatic encoder frame at a bottleneck layer is insufficient is relieved, and voice conversionwith many speakers to many speakers is achieved. According to the method, the defect that the representational capacity of the hidden variable in a VAE network on voice data is insufficient, and thevoice data can hardly be expanded to more complex voice data is overcome, the quality of converted voice is improved well, and the conversion performance is effectively improved. Dependency of the method on a parallel text is relieved, no aligning operation is needed in the training process, a conversion system with many source-target speaker pairs can be integrated in one conversion model, and many-to-many conversion is achieved.

Description

technical field [0001] The invention relates to a many-to-many voice conversion method, in particular to a beta-VAE-based many-to-many voice conversion method. Background technique [0002] After years of research on speech conversion technology, many classic conversion methods have emerged, including Gaussian Mixed Model (GMM), frequency bending, deep neural network (Deep Neural Network, DNN) and methods based on unit selection Wait. However, most of these speech conversion methods need to use parallel corpora for training, that is, the source speaker and the target speaker need to utter sentences with the same speech content and speech duration, and the pronunciation rhythm and emotion should be as consistent as possible. However, in the practical application of speech conversion, it is not easy to obtain a large amount of parallel corpus, or even unsatisfactory. In addition, the accuracy of the alignment of speech feature parameters during training has also become a cons...

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): G10L21/007G10L21/013
CPCG10L21/007G10L21/013
Inventor 李燕萍张成飞许吉良张燕
Owner NANJING UNIV OF POSTS & TELECOMM