Construction of model-space constraints
| Autor: | Patrick Nguyen, C. Wellekens, J.-C. Junqua, Luca Rigazio |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Computer science
business.industry Speech recognition Word error rate Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Pattern recognition Linear discriminant analysis Constraint (information theory) Piecewise linear function symbols.namesake Principal component analysis Redundancy (engineering) symbols Artificial intelligence Hidden Markov model business Gaussian process |
| Zdroj: | IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.. |
| DOI: | 10.1109/asru.2001.1034591 |
| Popis: | HMM systems exhibit a large amount of redundancy. To this end, a technique called eigenvoices was found to be very effective for speaker adaptation. The correlation between HMM parameters is exploited via a linear constraint called eigenspace. This constraint is obtained through a PCA of the training speakers. We show how PCA can be linked to the maximum-likelihood criterion. Then, we extend the method to LDA transformations and piecewise linear constraints. On the Wall Street Journal (WSJ) dictation task, we obtain 1.7% WER improvement (15% relative) when using self-adaptation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|