A speech generation method based on deep convolutional generative adversarial network

Abstract

The invention discloses a voice production method based on a deep convolutional generative adversarial network. The steps comprise: (1) acquiring voice signal samples; (2) preprocessing the voice signal samples; (3) inputting the voice signal samples to a deep convolutional generative adversarial network; (4) training the input voice signals; (5) generating voice signals similar to real voice contents. A tensorflow is used as a learning framework, and a deep convolutional generative adversarial network algorithm is used to train large quantity of voice signals. A dynamic game process of a distinguishing network D and a generation network G in the deep convolutional generative adversarial network is used to finally generate a natural voice signal close to original learning contents. The method generates voice based on the deep convolutional generative adversarial network, and solves problems that an intelligent device is overly dependent on a fixed voice library to sound in a man-machine face-to-face communication process, and mode is monotonous and is lack of variations and is not natural enough.

Description

technical field [0001] The invention belongs to the technical field of speech generation, and in particular relates to a speech generation method based on a deep convolution generation confrontation network. Background technique [0002] The research of human-computer interaction technology is an important part of the field of computer technology research. Making smart devices have the function of "speaking", which plays a very important role in the real "face-to-face human-computer communication". With the help of voice generation systems, smart devices can already speak clearly and naturally, which is easy for ordinary users to understand and accept. Voice imitation is an important part of human-machine voice communication. On the one hand, it is necessary to establish a large number of voice databases in the early stage. On the other hand, it needs to extract and train the features of a large number of voice signals to finally generate natural voice signals close to the ...

AI Technical Summary

Problems solved by technology

[0003] The generative confrontation network is a deep learning model that has become popular in recent years. It mainly uses tensorflow as a learning framework to train a generator G to generate realistic samples from random noise or latent variables, and at the same time train a discriminator Generator D is used to identify real data and generated data. Both are trained at the same time. G and D are used to form a dynamic "game process" until a Nash equilibrium is reached. The data generated by the generator is indistinguishable from real samples, and the discriminator cannot distinguish correctly. Generated and real data

Through the voice signal formed based on the generative confrontation network, it can overcome the shortcomings of current smart devices that can only speak according to a fixed voice library during man-machine dialogue, and the mode is monotonous and lacks change, which is not natural enough.

Images