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

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...

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

Images