Speech processing method, device, terminal equipment and storage medium

Abstract

The present application discloses a voice processing method, device, terminal equipment and storage medium. The method includes: acquiring noisy audio data, which includes a voice source signal; preprocessing the noisy audio data, and obtaining the noisy audio data from Extract noisy audio features from the data and input the pre-trained speech processing network model to obtain denoised audio features. The pre-trained speech processing network model includes multiple causal convolutional layers and at least one recursive neural network layer. A causal convolutional layer is used to output the texture feature of the corresponding speech source signal according to the noise frequency feature, and at least one recursive neural network layer is used to output the denoised audio feature according to the texture feature; according to the denoised audio feature, the speech is obtained An estimate of the source signal and output as denoised noisy audio data. The application realizes real-time noise reduction of noisy audio data through the causal convolution layer and the recursive neural network layer, and improves the voice noise reduction effect.

Description

technical field [0001] The present application relates to the technical field of audio data processing, and more specifically, to a voice processing method, device, terminal equipment, and storage medium. Background technique [0002] With the rapid development of communication technology and smart terminals, people's entertainment, social activities and other behaviors based on smart terminals are more and more free from geographical and time constraints. Not only can live broadcast, calls, chats, etc. Functional activities can also realize various functions outdoors. However, depending on the environment, the smart terminal often receives various background noises while receiving the voice input by the user, which affects the recognizability of the voice input by the user, and is not conducive to the user's various voice activities. Therefore, how to effectively suppress background noise when the user performs voice activities needs to be solved urgently. Contents of th...

AI Technical Summary

Problems solved by technology

However, depending on the environment, the smart terminal often receives various background noises while receiving the voice input by the user, which affects the recognizability of the voice input by the user, and is not conducive to the user's various voice activities. Therefore, how to effectively suppress background noise when users perform voice activities needs to be solved urgently.

Images