A simplified early auditory model with application in audio classification Un mod` ele auditif simplifi´ e avec application ` a la classification audio
Wei Chu · 2006
`The past decade has seen extensive research on audio classification and segmentation algorithms. However, the effect of background noise on classification performance has not been widely investigated. Recently, an early auditory model that calculates a so-called auditory spectrum has achieved excellent performance in audio classification along with robustness in a noisy environment. Unfortunately, this early auditory model is characterized by high computational requirements and the use of nonlinear processing. In this paper, certain modifications are introduced to develop a simplified version of this model which is linear except for the calculation of the square-root value of the energy. Speech/music and speech/non-speech classification tasks are carried out to evaluate the classification performance, with a support vector machine (SVM) as the classifier. Compared to a conventional fast Fourier transform‐based spectrum, both the original auditory spectrum and the proposed simplified auditory spectrum show more robust performance in noisy test cases. Test results also indicate that despite a reduced computational complexity, the performance of the proposed simplified auditory spectrum is close to that of the original auditory spectrum.