Diacritization, automatic segmentation and labeling for Levantine Arabic speech

It is generally acknowledged that a reliable speech corpus is necessary for any application involving speech processing. In this paper, we propose methods to improve the BBN/AUB DARPA Babylon Levantine Arabic speech corpus to increase its reliability and efficiency. For this purpose, correction of pronunciation, diacritization, and new transcription are performed manually along with automatic phoneme segmentation and labeling. The comparison with the original transcription of the corpus shows a clear improvement in the output results.

[1]  Fadi Biadsy,et al.  Google's cross-dialect Arabic voice search , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Muhammad Ghulam,et al.  Study on unique pharyngeal and uvular consonants in foreign accented Arabic , 2008, INTERSPEECH.

[3]  Mark Hasegawa-Johnson,et al.  Cross-Dialectal Data Transferring for Gaussian Mixture Model Training in Arabic Speech Recognition , 2012 .

[4]  Slim Abdennadher,et al.  Survey on common Arabic language forms from a speech recognition point of view , 2009 .

[5]  Rainer Gruhn,et al.  Novel Techniques for Dialectal Arabic Speech Recognition , 2012 .

[6]  Steve Young,et al.  The HTK hidden Markov model toolkit: design and philosophy , 1993 .

[7]  Nizar Habash,et al.  Arabic Diacritization through Full Morphological Tagging , 2007, NAACL.

[8]  Nizar Habash,et al.  Spoken Arabic Dialect Identification Using Phonotactic Modeling , 2009, SEMITIC@EACL.

[9]  Jean-Luc Gauvain,et al.  Transcription of arabic broadcast news , 2004, INTERSPEECH.

[10]  Ruhi Sarikaya,et al.  Maximum entropy modeling for diacritization of Arabic text , 2006, INTERSPEECH.

[11]  Jean-Luc Gauvain,et al.  Arabic Broadcast News Transcription Using a One Million Word Vocalized Vocabulary , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[12]  Shrikanth S. Narayanan,et al.  Automatic diacritization of Arabic transcripts for automatic speech recognition , 2005 .

[13]  Fayez A. Alhargan,et al.  Saudi accented Arabic voice bank , 2008, ExLing.

[14]  Steve Renals,et al.  WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[15]  Dimitra Vergyri,et al.  Automatic Diacritization of Arabic for Acoustic Modeling in Speech Recognition , 2004 .

[16]  Sherif Abdou,et al.  Recent progress in Arabic broadcast news transcription at BBN , 2005, INTERSPEECH.

[17]  King Abdulaziz,et al.  AUTOMATIC RESTORATION OF ARABIC DIACRITICS: A SIMPLE, PURELY STATISTICAL APPROACH , 2010 .

[18]  W. Marsden.  I and J , 2012 .

[19]  Ole Tange,et al.  GNU Parallel: The Command-Line Power Tool , 2011, login Usenix Mag..

[20]  Stuart M. Shieber,et al.  Arabic Diacritization Using Weighted Finite-State Transducers , 2005, SEMITIC@ACL.