A complete KALDI recipe for building Arabic speech recognition systems

Ahmed Ali, Yifan Zhang, Patrick Cardinal, Najim Dahak, Stephan Vogel, James Glass

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

93 Citations (Scopus)

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.

Original languageEnglish
Title of host publication2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages525-529
Number of pages5
ISBN (Electronic)9781479971299
DOIs
Publication statusPublished - 1 Apr 2014
Event2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - South Lake Tahoe, United States
Duration: 7 Dec 201410 Dec 2014

Publication series

Name2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings

Conference

Conference2014 IEEE Workshop on Spoken Language Technology, SLT 2014
Country/TerritoryUnited States
CitySouth Lake Tahoe
Period7/12/1410/12/14

Keywords

  • ASR system
  • Arabic
  • GALE
  • KALDI
  • Lexicon

Fingerprint

Dive into the research topics of 'A complete KALDI recipe for building Arabic speech recognition systems'. Together they form a unique fingerprint.

Cite this