Environment noise identification classification method based on convolutional neural network

Abstract

The invention relates to an environment noise identification classification method based on a convolutional neural network. The method comprises the following steps of: S1, extracting natural environment noise, and editing the natural environment noise into noise segments with duration of 300ms to 30s and a converted frequency of 44.1kHz; S2, carrying out short time Fourier transformation on the noise segments, and converting a one-dimensional time-domain signal into a two-dimensional time-domain signal to obtain a sonagraph; S3, extracting a MFCC (Mel Frequency Cepstrum Coefficient) of the signal; S4, forming a training set with 80% of all the noise segments and forming a testing set with the residual 20% of all the noise segments; S5, carrying out noise classification by a convolutionalneural network model; and S6, training a classification model by the training set, and verifying accuracy of the model by the testing set so as to complete environment noise identification classification based on the convolutional neural network. According to the invention, the sound segments are input, sound feature information is extracted, an output is a classification result, and automatic extraction on the sound feature information can be implemented.

Description

technical field [0001] The invention relates to an environmental noise recognition and classification method based on a convolutional neural network, which belongs to the field of environmental noise recognition. Background technique [0002] Sound recognition is a basic problem in sound signal processing. At present, most researches on audio classification and recognition are focused on speech recognition and music classification, and there are relatively few studies on the recognition and classification of environmental audio. With the improvement of environmental awareness, people pay more and more attention to how to eliminate noise pollution. In recent years, noise classification has become a topic of common concern at home and abroad, attracting domestic and foreign experts to discuss it. The accuracy of speech classification and recognition in the current clean environment is already very high, but in the case of low signal-to-noise ratio, or in the case of multiple p...

AI Technical Summary

Problems solved by technology

However, the support vector machine algorithm is difficult to implement on large-scale training samples and multi-classification problems, and SVM is sensitive to missing data

"Speech Recognition Based on Deep Neural Network" introduces the algorithm of speech recognition using BP neural network, but the learning speed of BP neural network is slow, even a simple problem requires hundreds of times of learning, and its network promotion ability limited

Images