Title :
Language modelling for Turkish as an agglutinative language
Author :
Ciloglu, T. ; Comez, M. ; Sahin, Seckin
Author_Institution :
Elektrik ve Elektron. Muhendisligi Bolumu, Orta Dogu Teknik Universitesi, Ankara, Turkey
Abstract :
Two types of language models have been considered for Turkish continuous speech recognition. In one case, words are separated into their stems and the rest, and language models are calculated based on this new set of units. In the other case, words are considered as a whole, but language models are calculated with respect to the stems of the words. Studies are carried out for bigram and trigram formalisms.
Keywords :
natural languages; speech recognition; Turkish language; agglutinative language; bigram formalism; continuous speech recognition; language modelling; trigram formalism; Natural languages; Speech recognition; Testing;
Conference_Titel :
Signal Processing and Communications Applications Conference, 2004. Proceedings of the IEEE 12th
Print_ISBN :
0-7803-8318-4
DOI :
10.1109/SIU.2004.1338563
