| Paper: | SLP-P17.7 | ||
| Session: | Spoken Language Modeling, Identification and Characterization | ||
| Time: | Thursday, May 18, 16:30 - 18:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: Language modeling and Adaptation | ||
| Title: | Morpheme-Based Language Modeling for Arabic LVCSR | ||
| Authors: | Ghinwa Choueiter, Massachusetts Institute of Technology, United States; Daniel Povey, Stanley Chen, Geoffrey Zweig, IBM T. J. Watson Research Center, United States | ||
| Abstract: | In this paper, we concentrate on Arabic speech recognition. Taking advantage of the rich morphological structure of the language, we use morpheme-based language modeling to improve the word error rate. We propose a simple constraining method to rid the decoding output of illegal morpheme sequences. We report the results obtained for word and morpheme language models using medium (<64kw) and large (~800kw) vocabularies, the morpheme LM obtaining an absolute improvement of 2.4% for the former and only 0.2% for the latter. The 2.4% gain surpasses previous gains for morpheme-based LMs for Arabic, and the large vocabulary runs represent the first comparative results for vocabularies of this size for any language. Finally, we analyze the performance of the morpheme LM on word OOV's. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012