A speech enhancement method using adaptive speech PDF

A speech enhancement algorithm by using MAP estimation with adaptive speech spectral amplitude probability density function (speech PDF) is presented in this paper. The proposed speech PDF has two adaptive shape parameters which affect the quality of enhanced speech. Noise can be efficiently suppressed when these parameters are properly estimated so that the adaptive speech PDF shape fits to the real-speech PDF one. We derive adaptive shape parameters from real-speech PDF in various narrow SNR intervals. The proposed speech enhancement algorithm with adaptive shape parameters is analyzed and compared to conventional algorithms. The evaluation results show that the proposed method is superior to the conventional algorithms.