Sound scene classification method based on network model fusion

Abstract

The invention discloses a sound scene classification method based on network model fusion. According to the method, multiple different input characteristics are created through a sound track separation mode, an audio cutting mode and other modes, gamma pass filter cepstrum coefficients, Mel spectral characteristics and first-order and second-order differences of audio signals are extracted to serve as the input characteristics, multiple different corresponding convolutional neural network models are trained respectively, and lastly a support vector machine stacking method is adopted to realizea final fusion model. Through the method, the audio input characteristics with strong recognition are extracted by the adoption of the sound track separation mode, the audio cutting mode and other modes, a single-channel convolutional neural network and a two-channel convolutional neural network are constructed, a unique model fusion structure is generated finally, richer and more stereoscopic information can be obtained, the recognition rate and robustness of different sound scene classifications are effectively improved, and the method has a good application prospect.

Description

technical field [0001] The invention relates to the technical field of acoustic scene classification, in particular to an acoustic scene classification method based on network model fusion. Background technique [0002] The sound scene classification technology is to use computing means to complete the classification of sound scenes according to the information contained in different sound scenes. This technology is of great significance in improving the automation of machines, allowing machines to automatically perceive environmental features, retrieve audio content, and improve the performance of multimedia electronic products. [0003] The features used in traditional acoustic scene classification mainly include: features such as zero-crossing rate and energy in the time domain or features in the frequency domain and cepstrum domain. Commonly used classification methods include: simple threshold judgment method, Gaussian Mixture Model (Gaussian MixtureModel, GMM) method,...

AI Technical Summary

Problems solved by technology

[0007] 2) The recognition ability of the pattern recognition algorithm is greatly affected by the change of the environment, and the robustness is poor;

[0008] 3) Traditional classifiers have weak classification ability and no learning ability

[0009] In addition, a video-based event detection method used in the prior art, due to adverse factors such as insufficient light, dim environment, and too much floating dust in the air, the returned video image is blurred, which is likely to cause misjudgment and missed judgment, as well as acoustic scene classification. , problems with low recognition rate and poor robustness

Images