Many-to-many speaker conversion method based on Transitive STARGAN

Abstract

The invention discloses a many-to-many speaker conversion method based on Transitive STARGAN. According to the invention, a STARGAN generator is combined with a transmission network, features extracted by a coding network are transmitted to a corresponding network layer of a decoding network in the generator; the learning capability of the decoding network on semantic features of different scalesis improved; the learning function of the model on the frequency spectrum deep features is realized; the frequency spectrum generation quality of the decoding network is improved, semantic features and personalized features of speakers are learned more fully, so that the personality similarity and voice quality of converted and synthesized voice are better improved, the problem that the personality similarity and the naturalness are poor after STARGAN model conversion is solved, and high-quality many-to-many speaker conversion under a non-parallel text condition is realized.

Description

technical field [0001] The invention relates to a multi-to-multiple speaker conversion method, in particular to a multi-to-multiple speaker conversion method based on TransitiveSTARGAN. 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, synthesis and speaker recognition. 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, while retaining semantic information, that is, to make the voice of the source speaker sound like the voice of the target speaker after conversion. . [0003] After years of research on speech conversion technology, many classic conversion methods have emerged. According to the classification of training corpus, they can be divided into conversion methods under parallel text conditions and conversion methods under non-parallel text condition...

AI Technical Summary

Problems solved by technology

[0007] Purpose of the invention: the technical problem to be solved in the present invention is to provide a Transitive STARGAN-based many-to-many speaker conversion method and computer storage medium, which solves the network degradation problem of the existing method in the training process, by using the STARGAN generator Multi-layer TransNet is built between the encoding and decoding networks to improve the learning ability of the decoding network for semantic features of different scales, realize the learning function of the model for deep spectral features, improve the quality of spectrum generation of the decoding network, and more fully learn semantic features and speakers. Personalized features, so as to better improve the personality similarity and voice quality of converted and synthesized speech

Images