Projection-based group delay scheme for speech recognition

Abstract

This paper deals with speech recognition in a noisy environment. Some robust properties of the group delay spectrum are derived, and a projection-based group delay scheme is proposed for noisy speech recognition. Experiments show that the proposed new scheme obtains better recognition results, especially under low signal-to-noise ratio (SNR) conditions. When the features of speech signals are obtained from the group delay spectrum, the continuous hidden Markov models (CHMMs) are used for speaker-dependent speech recognition. The robustness of the noisy group delay spectrum is analyzed through a noisy speech model and histograms, respectively. We apply the projection measure to the CHMM and derive the correlative formulas.