Speech synthesis method, vocoder training method and device, medium and electronic equipment

Abstract

The invention relates to a speech synthesis method, a vocoder training method and device, a medium and electronic equipment. The method comprises the steps of obtaining acoustic feature information ofeach speech frame corresponding to each phoneme in a to-be-synthesized text; and inputting the acoustic feature information of each speech frame into a vocoder to obtain audio information corresponding to the to-be-synthesized text, the vocoder being a vocoder based on an extended convolutional neural network. Since the extended convolutional neural network has the capability of processing data in parallel, the speed of speech synthesis can be improved and the training speed of the vocoder can be accelerated by performing speech synthesis through the vocoder based on the extended convolutional neural network. Moreover, the vocoder performs speech synthesis based on the acoustic feature information of each speech frame, and the acoustic feature information of each speech frame does not need to be extracted, so that the operand of the vocoder is reduced, and the speed of speech synthesis is further improved.

Description

technical field [0001] The present disclosure relates to the technical field of speech synthesis, and in particular, to a speech synthesis method, a vocoder training method, a device, a medium, and an electronic device. Background technique [0002] The speech synthesis vocoder reconstructs the speech waveform from the acoustic features such as fundamental frequency and frequency spectrum, which is an integral part of the speech synthesis system. Among them, the accuracy, naturalness and synthesis speed of the synthesized speech are the measures of the performance of the vocoder Important indicators. In recent years, with the successful application of deep neural network models in acoustic modeling, the accuracy and naturalness of speech synthesis have been effectively improved, but the speed of speech synthesis is not ideal. Therefore, how to increase the speed of speech synthesis while ensuring the accuracy and naturalness of the synthesized speech has become the research...

AI Technical Summary

Problems solved by technology

In recent years, with the successful application of deep neural network models in acoustic modeling, the accuracy and naturalness of speech synthesis have been effectively improved, but the speed of speech synthesis is not ideal

Images