Template-Based Continuous Speech Recognition
Authors:
- Mike MattonMMMike Matton
- Kris DemuynckKDKris Demuynck
- Patrick WambacqPWPatrick Wambacq
- Ronald CoolsRCRonald Cools
- Dirk Van CompernolleDCDirk Van Compernolle
- 23 April 2007
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 15 (4) , 1377-1390
Abstract
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 resultsKeywords
This publication has 24 references indexed in Scilit:
- Syllable-based large vocabulary continuous speech recognitionIEEE Transactions on Speech and Audio Processing, 2001
- An optimal algorithm for approximate nearest neighbor searching fixed dimensionsJournal of the ACM, 1998
- Gapped BLAST and PSI-BLAST: a new generation of protein database search programsNucleic Acids Research, 1997
- From HMM's to segment models: a unified view of stochastic modeling for speech recognitionIEEE Transactions on Speech and Audio Processing, 1996
- On the role of spectral transition for speech perceptionThe Journal of the Acoustical Society of America, 1986
- Frame-specific statistical features for speaker independent speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- On the application of embedded digit training to speaker independent connected digit recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- Processing interactions and lexical access during word recognition in continuous speechCognitive Psychology, 1978
- Multidimensional binary search trees used for associative searchingCommunications of the ACM, 1975
- Minimum prediction residual principle applied to speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975