Multi-style training of HMMS with stereo data for reverberation-robust speech recognition
Armin Sehr, Christian H. Hofmann, Roland Maas, Walter Kellermann · 2011
A novel training algorithm using data pairs of clean and reverberant feature vectors for estimating robust Hidden Markov Models (HMMs), introduced in for matched training, is employed in this paper for multi-style training. The multi-style HMMs are derived from well-trained clean-speech HMMs by aligning the clean data to the clean-speech HMM and using the resulting state-frame alignment to estimate the Gaussian mixture densities from the reverberant data of several different rooms. Thus, the temporal alignment is fixed for all reverberation conditions contained in the multi-style training set so that the model mismatch between the different rooms is reduced. Therefore, this training approach is particularly suitable for multi-style training. Multi-style HMMs trained by the proposed approach and adapted to the current room condition using maximum likelihood linear regression significantly outperform the corresponding adapted multi-style HMMs trained by the conventional Baum-Welch algorithm. In strongly reverberant rooms, the proposed adapted multi-style HMMs even outper-form Baum-Welch HMMs trained on matched data.