Deprecated: Array and string offset access syntax with curly braces is deprecated in /var/www/html/arg/administrator/components/com_jresearch/tables/publication.php on line 150

Deprecated: Array and string offset access syntax with curly braces is deprecated in /var/www/html/arg/administrator/components/com_jresearch/tables/publication.php on line 166

Non-Negative Matrix Factorization for Highly Noise-Robust ASR: to Enhance or to Recognize?

Weninger, Felix; Wöllmer, Martin; Geiger, Jürgen; Schuller, Björn; Gemmeke, Jort; Hurmalainen, Antti; Virtanen, Tuomas; Rigoll, Gerhard
Abstract

This paper proposes a multi-stream speech recognition system that combines information from three complementary analysis methods in order to improve automatic speech recognition in highly noisy and reverberant environments, as featured in the 2011 PASCAL CHiME Challenge. We integrate word predictions by a bidirectional Long Short-Term Memory recurrent neural network and non-negative sparse classification (NSC) into a multi-stream Hidden Markov Model using convolutive non-negative matrix factorization (NMF) for speech enhancement. Our results suggest that NMF-based enhancement and NSC are complementary despite their overlap in methodology, reaching up to 91.9% average keyword accuracy on the Challenge test set at signal-to-noise ratios from -6 to 9 dB-the best result reported so far on these data.

Keywords

NMF; speech recognition

Research areas

Year:
2012
Book title:
In proc. 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)