Search

The long-distance acoustic signal has low energy, high concealment and low signal-to-noise ratio (SNR), thus is often submerged in noise and interference. The conventional method of acoustic detection cannot classify or recognize the target. A sound recognition method has been proposed to simulate human ear auditory process by making the best of sound recognition advantage of human ear. First of all, those parts which function as energy gathering, frequency-selective amplification or information transmission in human ear are selected, and the auditory model of each part is established independently. Then, the structural parameters of each model are extracted, and the influence and change rules of structural parameters on the auditory signal are studied and optimized according to the auditory law. Finally, the auditory model is reconstructed based on the parameters extracted from each component, and the integrated model is used to carry out the voice recognition experiment under low SNR. The recognition rate of low SNR (−5 dB) acoustic event is improved by 6.5%.

Surrounded by low SNR, how to make the voice faster and better recognize the owner has become a heated research topic. The human auditory system can accurately acquire the characteristics of acoustic events in complex systems or low SNR noise environment, which is of significance in the research of bionic hearing of human ear. The response curve of human ear output is obtained by bionic technology, which is the best response curve for sound enhancement to modify Mel filter. The method of adaptive threshold selection is used to integrate Mel features to realize the reduction and dynamic extraction of low SNR speech features. This method not only can resist the disadvantages of poor robustness and complexity of parameter model, but also obtain dynamic and comprehensive speech information of different speakers in different scenes. Finally, the improved CNN and I-vector system are contributed to reduce the dimension of the data and to verify the recognition, so as to achieve the optimal frequency selective amplification and simplification of the acoustic signal. In the case of SNR-5db, the model is reduced by 15% and the recognition accuracy is improved by 3%.