Voice noise reduction method for conference terminal based on neural network model

Abstract

The invention provides a voice noise reduction method for a conference terminal based on the neural network model. The method comprises steps that S1, an audio file is collected by the conference terminal device to generate a digital audio signal in the time domain; S2, the digital audio signal is framed, and short-time Fourier transform is performed; S3, the amplitude spectrum of the frequency domain is mapped into a frequency band, and a Mel-frequency cepstral coefficient is further solved; S4, first-order and second-order differential coefficients are calculated through utilizing the Mel-frequency cepstral coefficient, a pitch correlation coefficient is calculated on each frequency band, and pitch period features and VAD features are further extracted; S5, input characteristic parameters of an audio are used as the input of the neural network model, the neural network is trained offline, the frequency band gain generating the noise reduction speech is learned, and the trained weightis solidified; S6, the neural network model is utilized to learn, the frequency band gain is generated, the outputted frequency band gain is mapped to the spectrum, the phase information is added, and a noise reduction speech signal is reduced through inverse Fourier transform. The method is advantaged in that real-time noise reduction can be achieved.

Description

technical field [0001] The invention relates to the technical fields of voice processing and communication, in particular to a neural network model-based voice noise reduction method for a conference terminal. Background technique [0002] Speech noise reduction technology refers to removing noise from noisy audio signals, and has a wide range of applications, such as mobile terminals and conference terminal equipment. The research on speech noise reduction technology has a long history, and monophonic speech noise reduction is a very challenging topic. Using only one microphone for speech noise reduction can not only reduce the cost of equipment, but also make it more convenient in actual use. [0003] In the prior art, the original amplitude spectrum is used as the input of the neural network. Too many input nodes lead to a large amount of calculation, which affects real-time voice communication, and requires further compression of the amplitude spectrum. The amplitude s...

AI Technical Summary

Problems solved by technology

The fewer output nodes, the smaller the amount of calculation, but at the same time, the error is larger when the difference is expanded, especially when the signal-to-noise ratio is low, some weaker speech signals will be significantly suppressed, resulting in intermittent sound

Images