Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/00ED0C02-D3BE-44AA-B964-C0F7FE113B99 | - |
| Identifier | http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=466659&url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel4%2F89%2F9789%2F00466659.pdf%3Farnumber%3D466659 | - |
| Identifier | https://doi.org/10.1109/89.466659 | - |
| Language | en | - |
| Extent | 10 pages | en |
| Title | Speaker adaptation using constrained estimation of Gaussian mixtures | en |
| Creator | Digalakis Vasilis | en |
| Creator | Διγαλακης Βασιλης | el |
| Creator | Rtischev D. | en |
| Creator | Neumeyer Leonardo | en |
| Publisher | Institute of Electrical and Electronics Engineers | en |
| Content Summary | A trend in automatic speech recognition systems is the use of continuous mixture-density hidden Markov models (HMMs). Despite the good recognition performance that these systems achieve on average in large vocabulary applications, there is a large variability in performance across speakers. Performance degrades dramatically when the user is radically different from the training population. A popular technique that can improve the performance and robustness of a speech recognition system is adapting speech models to the speaker, and more generally to the channel and the task. In continuous mixture-density HMMs the number of component densities is typically very large, and it may not be feasible to acquire a sufficient amount of adaptation data for robust maximum-likelihood estimates. To solve this problem, the authors propose a constrained estimation technique for Gaussian mixture densities. The algorithm is evaluated on the large-vocabulary Wall Street Journal corpus for both native and nonnative speakers of American English. For nonnative speakers, the recognition error rate is approximately halved with only a small amount of adaptation data, and it approaches the speaker-independent accuracy achieved for native speakers. For native speakers, the recognition performance after adaptation improves to the accuracy of speaker-dependent systems that use six times as much training data | en |
| Type of Item | Peer-Reviewed Journal Publication | en |
| Type of Item | Δημοσίευση σε Περιοδικό με Κριτές | el |
| License | http://creativecommons.org/licenses/by/4.0/ | en |
| Date of Item | 2015-11-02 | - |
| Date of Publication | 1995 | - |
| Subject | HMM | en |
| Subject | Hidden Markov Models | en |
| Subject | Speech recognition | en |
| Bibliographic Citation | V. Digalakis, D. Rtischev and L. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Process., vol. 3, no. 5, pp. 357-366, Sep. 1995. doi:10.1109/89.466659 | en |
Copyright © DIAS 2013
