Development of a TV broadcasts speech recognition system for Qatari Arabic

Mohamed Elmahdy, Mark Hasegawa-Johnson, Eiman Mustafawi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A major problem with dialectal Arabic speech recognition is due to the sparsity of speech resources. In this paper, a transfer learning framework is proposed to jointly use a large amount of Modern Standard Arabic (MSA) data and little amount of dialectal Arabic data to improve acoustic and language modeling. The Qatari Arabic (QA) dialect has been chosen as a typical example for an under-resourced Arabic dialect. A wide-band speech corpus has been collected and transcribed from several Qatari TV series and talk-show programs. A large vocabulary speech recognition baseline system was built using the QA corpus. The proposed MSA-based transfer learning technique was performed by applying orthographic normalization, phone mapping, data pooling, acoustic model adaptation, and system combination. The proposed approach can achieve more than 28% relative reduction in WER.

Original languageEnglish (US)
Title of host publicationProceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014
EditorsNicoletta Calzolari, Khalid Choukri, Sara Goggi, Thierry Declerck, Joseph Mariani, Bente Maegaard, Asuncion Moreno, Jan Odijk, Helene Mazo, Stelios Piperidis, Hrafn Loftsson
PublisherEuropean Language Resources Association (ELRA)
Pages3057-3061
Number of pages5
ISBN (Electronic)9782951740884
StatePublished - 2014
Event9th International Conference on Language Resources and Evaluation, LREC 2014 - Reykjavik, Iceland
Duration: May 26 2014May 31 2014

Publication series

NameProceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014

Other

Other9th International Conference on Language Resources and Evaluation, LREC 2014
Country/TerritoryIceland
CityReykjavik
Period5/26/145/31/14

Keywords

  • Dialectal Arabic
  • Speech recognition
  • Transfer learning

ASJC Scopus subject areas

  • Linguistics and Language
  • Library and Information Sciences
  • Education
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Development of a TV broadcasts speech recognition system for Qatari Arabic'. Together they form a unique fingerprint.

Cite this