Novel Techniques for Dialectal Arabic Speech Recognition

  • Mohamed Elmahdy
  • Rainer Gruhn
  • Wolfgang Minker

Table of contents

  1. Front Matter
    Pages I-XXI
  2. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 1-5
  3. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 7-23
  4. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 25-32
  5. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 33-51
  6. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 53-69
  7. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 71-80
  8. Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker
    Pages 81-85
  9. Back Matter
    Pages 87-110

About this book

Introduction

Novel Techniques for Dialectal Arabic Speech describes approaches to improve automatic speech recognition for dialectal Arabic. Since speech resources for dialectal Arabic speech recognition are very sparse, the authors describe how existing Modern Standard Arabic (MSA) speech data can be applied to dialectal Arabic speech recognition, while assuming that MSA is always a second language for all Arabic speakers.

In this book, Egyptian Colloquial Arabic (ECA) has been chosen as a typical Arabic dialect. ECA is the first ranked Arabic dialect in terms of number of speakers, and a high quality ECA speech corpus with accurate phonetic transcription has been collected. MSA acoustic models were trained using news broadcast speech. In order to cross-lingually use MSA in dialectal Arabic speech recognition, the authors have normalized the phoneme sets for MSA and ECA. After this normalization, they have applied state-of-the-art acoustic model adaptation techniques like Maximum Likelihood Linear Regression (MLLR) and Maximum A-Posteriori (MAP) to adapt existing phonemic MSA acoustic models with a small amount of dialectal ECA speech data. Speech recognition results indicate a significant increase in recognition accuracy compared to a baseline model trained with only ECA data.

Keywords

Arabic dialect Arabic speech recognition ECA ECA speech data MAP MLLR MSA

Authors and affiliations

  • Mohamed Elmahdy
    • 1
  • Rainer Gruhn
    • 2
  • Wolfgang Minker
    • 3
  1. 1.Qatar UniversityDohaQatar
  2. 2.SVOX Deutschland GmbHUlmGermany
  3. 3., Institute of Information TechnologyUniversity of UlmUlmGermany

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4614-1906-8
  • Copyright Information Springer Science+Business Media New York 2012
  • Publisher Name Springer, Boston, MA
  • eBook Packages Engineering
  • Print ISBN 978-1-4614-1905-1
  • Online ISBN 978-1-4614-1906-8
  • About this book
Industry Sectors
Pharma
Automotive
Biotechnology
Electronics
Telecommunications
Consumer Packaged Goods
Aerospace
Oil, Gas & Geosciences