利用冲击声辨识声源材料的特征提取

Feature extraction for sound source material recognition with impact sounds

声源辨识属于环境声识别的范畴,是模式识别的一个重要研究方向。冲击声携带了大量的声源物理信息,因此利用冲击声提取特征进行声源材料辨识是提高声目标识别分类性能的重要途径。对球-板撞击物理模型合成的冲击声连续统,提出使用基函数学习法提取目标特征,同时利用短时傅里叶变换和小波包变换进行特征提取,以此为基础完成被击平板的材料识别。研究结果表明,利用基函数学习法获得的特征,对于冲击声分类的效果明显优于短时傅里叶变换和小波包变换方法,说明利用该方法进行冲击声声源材料辨识的可行性和优势。

Sound source recognition belongs to environmental sound recognition, which is one of the most important research areas for pattern recognition. Impact sounds carry much physical information about the sound sources, which makes impact sound based sound source recognition an important method to improve recognition performance. The impact sound continum synthesized with a ball-plate collision model are used for material recognition of the impacted plates. The basis function learning method and time-frequency representation methods, including the short time Fourier transform and the wavelet packet transform, are applied into classification and the recognition results are compared. The result shows that the feature obtained by using the basis function learning method performs better for classification of the material of the impacted plates than that by using the short time Fourier transform and the wavelet packet transform. This demonstrates the efficiency and superiority of this method in material recognition of sound sources.