Robust Speech and Bird Song Processing using Multi-band Correlograms and Sparse Representations

of the Dissertation Robust Speech and Bird Song Processing using Multi-band Correlograms and Sparse Representations by Lee Ngee Tan Doctor of Philosophy in Electrical Engineering University of California, Los Angeles, 2014 Professor Abeer Alwan, Chair This dissertation focuses on algorithms for robust speech and bird song processing. Many applications perform well under ideal signal conditions, e.g. noisefree, full bandwidth, sufficient training data. However, a large degradation in performance is generally observed when the input signal condition deviates from these ideal conditions. This dissertation describes robust algorithms for three applications, namely human-pitch detection, automatic speech recognition, and birdsong phrase classification. In the first application, a noise-robust, multi-band summary correlogram (MBSC)-based pitch detector is proposed. Novel signal processing schemes, which include comb-filter channel selection and subband reliability weighting, are designed to enhance the MBSC’s peak at the most likely pitch period. In the second application, a feature enhancement scheme using jointly-sparse reference and estimated soft-mask representations, is developed for noise-robust automatic speech recognition (ASR). Reference and estimated soft-mask exemplarpairs are extracted from clean and noisy utterance-pairs in the training data.