Speech synthesis method and device, readable storage medium and electronic equipment

Abstract

The invention relates to a voice synthesis method and device, a readable storage medium and electronic equipment. The method comprises the steps of determining acoustic feature information corresponding to a to-be-synthesized text; obtaining audio information corresponding to the to-be-synthesized text through a first vocoder according to the acoustic characteristic information, wherein the firstvocoder is obtained by carrying out knowledge distillation on a second vocoder, the first vocoder and the second vocoder are vocoders based on a neural network model, and the model complexity of the first vocoder is lower than that of the second vocoder. Thus, the first vocoder learns the excellent data processing capability of the second vocoder, has a simple model structure, and has two advantages of accuracy and speed. Thus, speech synthesis is performed on the to-be-synthesized text based on the first vocoder, and a speech synthesis result can be quickly obtained on the basis of ensuring speech synthesis accuracy.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to a speech synthesis method, device, readable storage medium and electronic equipment. Background technique [0002] A vocoder constructs a speech waveform based on acoustic characteristics (eg, fundamental frequency, frequency spectrum, etc.) to form synthesized audio. It can be seen that the vocoder is a very important part of speech synthesis technology. The accuracy and speed of speech synthesis are important indicators to measure the performance of the vocoder. At present, with the popularity of neural network applications, neural network vocoders can be obtained based on neural network training. In order to ensure the accuracy of speech synthesis, neural network vocoders need to have complex network structures. However, on the one hand, complex structures The vocoder needs to spend a lot of training time in the early training, and the training efficiency and...

AI Technical Summary

Problems solved by technology

At present, with the popularity of neural network applications, neural network vocoders can be obtained based on neural network training. In order to ensure the accuracy of speech synthesis, neural network vocoders need to have complex network structures. However, on the one hand, complex structures The vocoder needs a lot of training time in the early training, the training efficiency and the real-time rate of the model are low. On the other hand, the vocoder obtained from training is not fast enough due to the complex internal structure.

Images