@inproceedings{a71d1e6e80b944d586b420045660f4b2,
title = "A complete KALDI recipe for building Arabic speech recognition systems",
abstract = "In this paper we present a recipe and language resources for training and testing Arabic speech recognition systems using the KALDI toolkit. We built a prototype broadcast news system using 200 hours GALE data that is publicly available through LDC. We describe in detail the decisions made in building the system: using the MADA toolkit for text normalization and vowelization; why we use 36 phonemes; how we generate pronunciations; how we build the language model. We report results using state-of-the-art modeling and decoding techniques. The scripts are released through KALDI and resources are made available on QCRI's language resources web portal. This is the first effort to share reproducible sizable training and testing results on MSA system.",
keywords = "ASR system, Arabic, GALE, KALDI, Lexicon",
author = "Ahmed Ali and Yifan Zhang and Patrick Cardinal and Najim Dahak and Stephan Vogel and James Glass",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 ; Conference date: 07-12-2014 Through 10-12-2014",
year = "2014",
month = apr,
day = "1",
doi = "10.1109/SLT.2014.7078629",
language = "English",
series = "2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "525--529",
booktitle = "2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings",
address = "United States",
}