Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/6BAF4883-036A-47B4-8A7B-A640F68EB6C9 | - |
| Αναγνωριστικό | http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=506931&url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel4%2F89%2F11102%2F00506931 | - |
| Αναγνωριστικό | https://doi.org/10.1109/89.506931 | - |
| Γλώσσα | en | - |
| Μέγεθος | 9 pages | en |
| Τίτλος | Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers | en |
| Δημιουργός | Digalakis Vasilis | en |
| Δημιουργός | Διγαλακης Βασιλης | el |
| Δημιουργός | Monaco P. | en |
| Δημιουργός | Murveit H. | en |
| Εκδότης | Institute of Electrical and Electronics Engineers | en |
| Περίληψη | An algorithm is proposed that achieves a good tradeoff between modeling resolution and robustness by using a new, general scheme for tying of mixture components in continuous mixture-density hidden Markov model (HMM)-based speech recognizers. The sets of HMM states that share the same mixture components are determined automatically using agglomerative clustering techniques. Experimental results on ARPA's Wall Street Journal corpus show that this scheme reduces errors by 25% over typical tied-mixture systems. New fast algorithms for computing Gaussian likelihoods-the-most time-consuming aspect of continuous-density HMM systems-are also presented. These new algorithms-significantly reduce the number of Gaussian densities that are evaluated with little or no impact on speech recognition accuracy | en |
| Τύπος | Peer-Reviewed Journal Publication | en |
| Τύπος | Δημοσίευση σε Περιοδικό με Κριτές | el |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2015-11-02 | - |
| Ημερομηνία Δημοσίευσης | 1996 | - |
| Θεματική Κατηγορία | HMM | en |
| Θεματική Κατηγορία | Hidden Markov Model | en |
| Θεματική Κατηγορία | Speech recognition | en |
| Βιβλιογραφική Αναφορά | V. Digalakis, P. Monaco and H. Murveit, "Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers," IEEE Trans. Speech Audio Process., vol. 4, no. 4, pp. 281-289, Jul. 1996. doi:10.1109/89.506931 | en |
Copyright © DIAS 2013
