Multi-style training of HMMS with stereo data for reverberation-robust speech recognition

Sehr A, Hofmann C, Maas R, Kellermann W (2011)


Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2011

Pages Range: 196-199

Article Number: 5942396

Event location: Edinburgh GB

ISBN: 9781457709999

DOI: 10.1109/HSCMA.2011.5942396

Abstract

A novel training algorithm using data pairs of clean and reverberant feature vectors for estimating robust Hidden Markov Models (HMMs), introduced in [1] 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. © 2011 IEEE.

Authors with CRIS profile

How to cite

APA:

Sehr, A., Hofmann, C., Maas, R., & Kellermann, W. (2011). Multi-style training of HMMS with stereo data for reverberation-robust speech recognition. In Proceedings of the 2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11 (pp. 196-199). Edinburgh, GB.

MLA:

Sehr, Armin, et al. "Multi-style training of HMMS with stereo data for reverberation-robust speech recognition." Proceedings of the 2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11, Edinburgh 2011. 196-199.

BibTeX: Download