Recent advances in ASR Applied to an Arabic transcription system for Al-Jazeera

Patrick Cardinal, Ahmed Ali, Najim Dehak, Yu Zhang, Tuka Al Hanai, Yifan Zhang, James Glass, Stephan Vogel

Research output: Contribution to journalConference articlepeer-review

Abstract

This paper describes a detailed comparison of several state-of-the-art speech recognition techniques applied to a limited Arabic broadcast news dataset. The different approaches were all trained on 50 hours of transcribed audio from the Al-Jazeera news channel. The best results were obtained using i-vector-based speaker adaptation in a training scenario using the Minimum Phone Error (MPE) criteria combined with sequential Deep Neural Network (DNN) training. We report results for two different types of test data: broadcast news reports, with a best word error rate (WER) of 17.86%, and a broadcast conversations with a best WER of 29.85%. The overall WER on this test set is 25.6%.

Keywords

  • ASR system
  • Arabic
  • Kaldi

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'Recent advances in ASR Applied to an Arabic transcription system for Al-Jazeera'. Together they form a unique fingerprint.

Cite this