Noise removing method in intelligent calling system based on machine learning

A machine learning and calling system technology, applied in instruments, automatic switching offices, telephone communications, etc., can solve problems such as poor noise reduction effect, audio distortion, and inability to remove noise segments, so as to reduce workload and avoid accidental deletion of people Sound, the effect of improving the recognition accuracy

Active Publication Date: 2020-03-27
HANGZHOU ZHEXIN IT TECHNOLOGY CO LTD
View PDF18 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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 te

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Noise removing method in intelligent calling system based on machine learning
  • Noise removing method in intelligent calling system based on machine learning
  • Noise removing method in intelligent calling system based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0034] Such as figure 1 As shown, the method for removing noise in an intelligent call system based on machine learning according to an embodiment of the present invention includes:

[0035] Step 1. Use sampled telephone signals as training data, and build a noise classification model based on machine learning. The step 1 specifically includes:

[0036] Step 101: Perform slicing processing, namely, VAD slicing, on the telephone signal, and perform normalization and frame preprocessing on the sliced ​​signal.

[0037] Since the volume of the slice signal is different, some of the signal has a higher volume, and some of the signal has a lighter sound. Normalizing the phone signal can help improve the recognition rate. In the preprocessing, the formula (1) is used for normalization processing, the slice signal is uniformly quantized by 16 ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): H04M3/18H04M3/50G10L21/0208G10L21/0232
CPCG10L21/0208G10L21/0232H04M3/18H04M3/50
Inventor 伍林尹朝阳
Owner HANGZHOU ZHEXIN IT TECHNOLOGY CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap