Hybrid input spaces for exemplar-based noise robust speech recognition using coupled dictionaries


Exemplar-based feature enhancement successfully exploits a wide temporal signal context. We extend this technique with hybrid input spaces that are chosen for a more effective separation of speech from background noise. This work investigates the use of two different hybrid input spaces which are formed by incorporating the full-resolution and modulation envelope spectral representations with the Mel features. A coupled output dictionary containing Mel exemplars, which are jointly extracted with the hybrid space exemplars, is used to reconstruct the enhanced Mel features for the ASR back-end. When compared to the system which uses Mel features only as input exemplars, these hybrid input spaces are found to yield improved word error rates on the AURORA-2 database especially with unseen noise cases.

23rd European Signal Processing Conference (EUSIPCO), Nice, France
Deepak Baby
Deepak Baby
Applied Scientist

My research interests include speech recognition, enhancement and deep learning.

Hugo Van hamme
Hugo Van hamme

Professor at KU Leuven, Belgium

comments powered by Disqus