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.