Proceedings of Meetings on Acoustics

Estimation of the power spectral density (PSD) of noise is crucial for retrieving speech in a noisy environment. 3 novel methods for estimating the non-white noise PSD of noisy speech based on a generalized gamma distribution and 3 criterions are proposed, which are minimum mean square error (MMSE), maximum a posteriori (MAP) and Maximum likelihood estimation (MLE). Because of the highly non-stationary nature of speech, it is difficult to derive the real probability density function (PDF) using any modeling technique. On the other hand, segmental noise is more stationary and can be fitted more accurately by a generalized gamma PDF, which is a natural extension of the Gaussian modeling for the distribution of non-white components. The results show that non-white noise spectrum fit more accurately on the generalized gamma PDF with adaptive parameters than on a Gaussian distribution function. The reported generalized gamma PDF model shows the better performance in estimating noise PSD compared to minimum statistics, MMSE-based and MLE noise PSD estimation methods. The performance of the proposed noise estimation is good when it is integrated with the speech-enhancement technique, as demonstrated log error, segmental SNR and PESQ measures.