Using x-gram for efficient speech recognition
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/106909
Tipus de documentText en actes de congrés
Data publicació1998
EditorRobert H. Mannel and Jordi Robert-Ribes
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
X-grams are a generalization of the n-grams, where the number of previous conditioning words is different for each case and decided from the training data. X-grams reduce perplexity with respect to trigrams and need less number of parameters. In this paper, the representation of the x-grams using finite state automata is considered. This representation leads to a new model, the non-deterministic x-grams, an approximation that is much more efficient, suffering small degradation on the modeling capability. Empirical experiments for a continuous speech recognition task show how, for each ending word, the number of transitions is reduced from 1222 (the size of the lexicon) to around 66.
CitacióBonafonte, A., Mariño, J.B. Using x-gram for efficient speech recognition. A: International Conference on Spoken Language Processing. "ICSLP 1998: International Conference on Spoken Language Processing: Sydney, Australia: November 30-December 4, 1998". Sidney: Robert H. Mannel and Jordi Robert-Ribes, 1998, p. 2559-2562.
ISBN1 876346 17 5
Versió de l'editorhttp://www.isca-speech.org/archive/icslp_1998/index.html
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
i98_1125.pdf | 61,60Kb | Visualitza/Obre |