Modelling Spectro-Temporal Dynamics in Factorisation-Based Noise-Robust Automatic Speech Recognition

Non-negative spectral factorisation has been used successfully for separation of speech and noise in automatic speech recognition, both in feature-enhancing front-ends and in direct classification. In this work, we propose employing spectro-temporal 2D filters to model dynamic properties of Mel-scale spectrogram patterns in ad-dition to static magnitude features. The results are evaluated using an exemplar-based sparse classifier on the CHiME noisy speech database. After optimisation of static features and modelling of tem-poral dynamics with derivative features, we achieve 87.4 % average score over SNRs from 9 to-6 dB, reducing the word error rate by 28.1 % from our previous static-only features. Index Terms — Automatic speech recognition, exemplar-based, spectral factorisation, noise robustnes