Feature extraction for sound source material recognition with impact sounds

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.