Automatic determination of acoustic model topology using variational Bayesian estimation and clustering for large vocabulary continuous speech recognition
| Autor: | Shinji Watanabe, Atsushi Nakamura, Atsushi Sako |
|---|---|
| Rok vydání: | 2006 |
| Předmět: |
Bayes estimator
Acoustics and Ultrasonics business.industry Speech recognition Decision tree Acoustic model Pattern recognition Mixture model Speech processing Topology ComputingMethodologies_PATTERNRECOGNITION Computer Science::Sound Search algorithm Artificial intelligence Electrical and Electronic Engineering business Hidden Markov model Cluster analysis Mathematics |
| Zdroj: | IEEE Transactions on Audio, Speech and Language Processing. 14:855-872 |
| ISSN: | 1558-7916 |
| DOI: | 10.1109/tsa.2005.857791 |
| Popis: | We describe the automatic determination of a large and complicated acoustic model for speech recognition by using variational Bayesian estimation and clustering (VBEC) for speech recognition. We propose an efficient method for decision tree clustering based on a Gaussian mixture model (GMM) and an efficient model search algorithm for finding an appropriate acoustic model topology within the VBEC framework. GMM-based decision tree clustering for triphone HMM states features a novel approach designed to reduce the overly large number of computations to a practical level by utilizing the statistics of monophone hidden Markov model states. The model search algorithm also reduces the search space by utilizing the characteristics of the acoustic model. The experimental results confirmed that VBEC automatically and rapidly yielded an optimum model topology with the highest performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|