Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Fast algorithms for phone classification and recognition using segment-based models

Digalakis Vasilis, Ostendorf M., Rohlicek J. R.

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/E2EA7355-151C-41CB-BE98-13BD40A3AD48-
Αναγνωριστικόhttp://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=175733&url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel4%2F78%2F4466%2F00175733.pdf%3Farnumber%3D175733-
Αναγνωριστικόhttps://doi.org/10.1109/78.175733-
Γλώσσαen-
Μέγεθος12 pagesen
ΤίτλοςFast algorithms for phone classification and recognition using segment-based modelsen
ΔημιουργόςDigalakis Vasilisen
ΔημιουργόςΔιγαλακης Βασιληςel
ΔημιουργόςOstendorf M.en
ΔημιουργόςRohlicek J. R.en
ΕκδότηςInstitute of Electrical and Electronics Engineersen
ΠερίληψηMethods for reducing the computation requirements of joint segmentation and recognition of phones using the stochastic segment model are presented. The approach uses a fast segment classification method that reduces computation by a factor of two to four, depending on the confidence of choosing the most probable model. A split-and-merge segmentation algorithm is proposed as an alternative to the typical dynamic programming solution of the segmentation and recognition problem, with computation savings increasing proportionally with model complexity. Although the current recognizer uses context-independent phone models, the results reported for the TIMIT database for speaker-independent joint segmentation and recognition are comparable to those of systems that use context informationen
ΤύποςPeer-Reviewed Journal Publicationen
ΤύποςΔημοσίευση σε Περιοδικό με Κριτέςel
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2015-11-02-
Ημερομηνία Δημοσίευσης1992-
Θεματική ΚατηγορίαSpeech recognitionen
Βιβλιογραφική ΑναφοράV. Digalakis, M. Ostendorf and J. R. Rohlicek, "Fast algorithms for phone classification and recognition using segment-based models," IEEE Trans. Signal Process., vol. 40, no. 12, pp. 2885-2896, Dec. 1992. doi:10.1109/78.175733en

Υπηρεσίες

Στατιστικά