Invited paper: Automatic speech recognition: History, methods and challenges
Pattern Recognition
Journal of Computational and Applied Mathematics
Dual stream speech recognition using articulatory syllable models
International Journal of Speech Technology
International Journal of Speech Technology
Trends and advances in speech recognition
IBM Journal of Research and Development
Speech recognition on mobile devices
Mobile Multimedia Processing
A segmental non-parametric-based phoneme recognition approach at the acoustical level
Computer Speech and Language
A hybrid approach based on DCT-Genetic-Fuzzy inference system for speech recognition
IDEAL'12 Proceedings of the 13th international conference on Intelligent Data Engineering and Automated Learning
Modelling non-stationary noise with spectral factorisation in automatic speech recognition
Computer Speech and Language
Classifying Immunophenotypes With Templates From Flow Cytometry
Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics
Hi-index | 0.00 |
Despite their known weaknesses, hidden Markov models (HMMs) have been the dominant technique for acoustic modeling in speech recognition for over two decades. Still, the advances in the HMM framework have not solved its key problems: it discards information about time dependencies and is prone to overgeneralization. In this paper, we attempt to overcome these problems by relying on straightforward template matching. The basis for the recognizer is the well-known DTW algorithm. However, classical DTW continuous speech recognition results in an explosion of the search space. The traditional top-down search is therefore complemented with a data-driven selection of candidates for DTW alignment. We also extend the DTW framework with a flexible subword unit mechanism and a class sensitive distance measure-two components suggested by state-of-the-art HMM systems. The added flexibility of the unit selection in the template-based framework leads to new approaches to speaker and environment adaptation. The template matching system reaches a performance somewhat worse than the best published HMM results for the Resource Management benchmark, but thanks to complementarity of errors between the HMM and DTW systems, the combination of both leads to a decrease in word error rate with 17% compared to the HMM results