Using a DBN to integrate Sparse Classification and GMM-based ASR

The performance of an HMM-based speech recognizer using MFCCs as input is known to degrade dramatically in noisy conditions. Recently, an exemplar-based noise robust ASR approach, sparse classification (SC) was introduced. While very successful at lower SNRs, the performance at high SNRs suffered when compared to HMM-based systems. In this work, we propose to use a Dynamic Bayesian Network (DBN) to implement an HMM-model that uses both MFCCs and phone predictions extracted from the SC system as input. By doing experiments on the AURORA-2 connected digit recognition task, we show that our approach successfully combines the strengths of both systems, resulting in competitive recognition accuracies at both high and low SNRs.