Template-Based Continuous Speech Recognition
| Autor: | M. De Wachter, Patrick Wambacq, Kris Demuynck, D. Van Compernolle, Mike Matton, Ronald Cools |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
Dynamic time warping
Acoustics and Ultrasonics Computer science business.industry Speech recognition Template matching Word error rate Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Pattern recognition Speech processing ComputingMethodologies_PATTERNRECOGNITION Computer Science::Sound Pattern recognition (psychology) Benchmark (computing) Pattern matching Artificial intelligence Electrical and Electronic Engineering Hidden Markov model business |
| Zdroj: | BASE-Bielefeld Academic Search Engine |
| ISSN: | 1558-7916 |
| DOI: | 10.1109/tasl.2007.894524 |
| Popis: | 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 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|