Mapping Sparse Representation to State Likelihoods in Noise-Robust Automatic Speech Recognition

This paper proposes learning-based methods for mapping a sparse representation of noisy speech to state likelihoods in an automatic speech recognition system. We represent speech as a sparse linear combination of exemplars extracted from training data. The weights of exemplars are mapped to speech state like-lihoods using Ordinary Least Squares (OLS) and Partial Least Squares (PLS) regression. Recognition experiments are con-ducted using the CHiME noisy speech database. According to the results, both algorithms can be successfully used for train-ing the mapping. We achieve improvements over the previous binary labeling system, and recognition scores close to 70 % at-6 dB SNR. Index Terms: automatic speech recognition, sparse representa-tions, exemplar-based, regressio