Speech Enhancement Based on Speech Spectral Complex Gaussian Mixture Model
Guohong Ding, Xia Wang, Yang Cao, Feng Ding, Yuezhong Tang · 2006
The paper presents a speech enhancement approach based on speech spectral complex Gaussian mixture model (GMM). First, a speech spectral GMM construction algorithm is introduced and it is based on the distance measure of speech spectral Gaussian probability. Then, a noise estimation algorithm based on the GMM is proposed in the maximum likelihood criterion using the expectation-maximisation (EM) algorithm. Speech enhancement experimental results show that the GMM-based MMSE estimators, especially the GMM-based MMSE short-time spectral estimator, can afford better performance than alternative speech enhancement algorithms, and the proposed noise estimation algorithm can improve the enhancement performance more, especially at low SNRs.