In this paper a multi-channel speech enhancement framework for distant speech acquisition in noisy and reverberant environments for Non-negative Matrix Factorization (NMF)-based Automatic Speech Recognition (ASR) is proposed. The system is evaluated for its use in an assistive vocal interface for physically impaired and speech-impaired users. The framework utilises the Spatially Pre-processed Speech Distortion Weighted Multi-channel Wiener Filter (SP-SDW-MWF) in combination with a postfilter to reduce noise and reverberation. Additionally, the estimation uncertainty of the speech enhancement framework is propagated through the Mel-Frequency Cepstrum Coefficients (MFCC) feature extraction to allow for feature compensation in a later stage. Results indicate that a) using a trade-off parameter between noise reduction and speech distortion has a positive effect on the recognition performance with respect to the well-known GSC and MWF and b) the addition of a post-filter and the feature compensation increases performance with respect to several baselines for a non-pathological and pathological speaker.
Cite as: Dekkers, G., Waterschoot, T.v., Vanrumste, B., Broeck, B.V.D., Gemmeke, J.F., Van hamme, H., Karsmakers, P. (2015) A multi-channel speech enhancement framework for robust NMF-based speech recognition for speech-impaired users. Proc. Interspeech 2015, 746-750, doi: 10.21437/Interspeech.2015-249
@inproceedings{dekkers15_interspeech,
author={Gert Dekkers and Toon van Waterschoot and Bart Vanrumste and Bert Van Den Broeck and Jort F. Gemmeke and Hugo {Van hamme} and Peter Karsmakers},
title={{A multi-channel speech enhancement framework for robust NMF-based speech recognition for speech-impaired users}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={746--750},
doi={10.21437/Interspeech.2015-249}
}