Non-negative matrix deconvolution in noise robust speech recognition

High noise robustness has been achieved in speech recognition by using sparse exemplar-based methods with spectrogram windows spanning up to 300 ms. A downside is that a large exemplar dictionary is required to cover sufficiently many spectral patterns and their temporal alignments within windows. We propose a recognition system based on a shift-invariant convolutive model, where exemplar activations at all the possible temporal positions jointly reconstruct an utterance. Recognition rates are evaluated using the AURORA2 database, containing spoken digits with noise ranging from clean speech to -5 dB SNR. We obtain results superior to those, where the activations were found independently for each overlapping window.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Antti Hurmalainen, Jort F. Gemmeke, Tuomas Virtanen
• Keywords: ICASSP 2011, Possible Temporal Positions, Shift-invariant Convolutive Model, Signal Processing, Sparse Exemplar-based Methods