Urban sound event classifying method based on N-DenseNet and high-dimensional mfcc features

Abstract

The invention provides an urban sound event classifying method based on an N-DenseNet and high-dimensional mfcc feature. By the urban sound event classifying method, during audio data processing, richer and more efficient feature information can be provided, ta model has stronger generalization ability, and classification has higher accuracy. The urban sound event classifying method comprises thefollowing steps: S1, acquiring audio data to be processed, preprocessing an original audio signal, and outputting an audio frame sequence; S2, performing time-domain and frequency-domain analysis on the audio frame sequence, extracting a high-dimensional Mel-frequency cepstrum coefficient, and outputting a feature vector sequence; S3, constructing an acoustic model, and training the acoustic modelto obtain a well-trained acoustic model; S4, processing the feature vector sequence output in the step S2, and then inputting into the well-trained acoustic model for classification recognition to obtain a recognition result, namely a classification result of a sound event, wherein the acoustic model is a network model constructed by combining the characteristics of an N-order Markov model on thebasis of a DenseNet model, namely the acoustic model is an N-order DenseNet model.

Description

technical field [0001] The invention relates to the technical field of sound recognition, in particular to an urban sound event classification method based on N-DenseNet and high-dimensional mfcc features. Background technique [0002] Building smart city complexes in modern society is a trend in urban development. Among them, using a huge sensor network to collect various data such as air quality, noise levels, and population activities in the target city, and analyzing the audio data to guide urban design is one of the ideas for building a smart city. Among them, the main research significance of studying the classification of urban sound events lies in noise monitoring, urban security, soundscape assessment, and multimedia retrieval. [0003] DenseNet is a convolutional neural network with dense connections. In this network, there is a direct connection between any two layers. The input of each layer of the network is the union of the outputs of all previous layers, and...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of insufficient sound classification feature extraction, insufficient generalization ability of the model, and low classification accuracy, the present invention provides a method for classifying urban sound events based on N-DenseNet and high-dimensional mfcc features. The data can provide rich and effective feature information, the model has strong generalization ability, and the classification has higher accuracy

Images