Noise removing method in intelligent calling system based on machine learning

Abstract

The invention discloses a noise removal method in an intelligent calling system based on machine learning, which comprises the following steps: slicing, normalizing and framing telephone signals; extracting MFCC features from the framed slice signals and carrying out averaging processing on the MFCC features; inputting the averaged MFCC features into a machine learning classifier for model training, wherein the trained classification model is used as a noise classification model; slicing the newly added telephone signal; carrying out normalization and framing preprocessing on the slice signals; carrying out frequency spectrum flatness preliminary screening on the framed slice signals; extracting MFCC features and then averaging the MFCC features; and inputting the MFCC features of each segment of signal after average processing into a noise classification model for identification. The beneficial effects of the method are that the method achieves the recognition of the voice or noise ofa signal through the classification model based on machine learning, can remove a large number of noise signals in a telephone signal, and reduces the error rate that the signal is transmitted to anASR and translated into characters.

Description

Technical field [0001] The present invention relates to the technical field of audio processing, and in particular to a method for removing noise in an intelligent call system based on machine learning. Background technique [0002] In the existing intelligent call system, the telephone signal will be intercepted by VAD, and then sent to ASR to be converted into text. Due to the complexity of the background, there are a lot of noise fragments. The usual processing method is to use noise suppression methods to filter the signal before the signal is intercepted. It is mainly based on the frequency distribution of the signal to estimate the noise. Commonly used algorithms include adaptive filters, spectral subtraction, and Wiener filtering. The adaptive filter uses the filter parameters obtained at the previous moment to automatically adjust the current filter parameters to adapt to the statistical characteristics of the random changes of the signal and noise, thereby achieving noi...

AI Technical Summary

Problems solved by technology

These noise suppression methods can only filter part of the noise, but cannot completely remove the intercepted noise segment, and as the signal-to-noise ratio in the telephone signal decreases, the noise reduction effect becomes worse, and there will be some periods of time due to excessive noise. Audio distortion caused by attenuation

Images