The IBM 2006 Gale Arabic ASR System

Hagen Soltau, George Saon, Brian Kingsbury, Hong-Kwang Jeff Kuo, Lidia Mangu, Daniel Povey, Geoffrey ZweigICASSP 2007 · OpenReview

Abstract

This paper describes the advances made in IBM's Arabic broadcast news transcription system which was fielded in the 2006 GALE ASR and machine translation evaluation. These advances were instrumental in lowering the word error rate by 42% relative over the course of one year and include: training on additional LDC data, large-scale discriminative training on 1800 hours of unsupervised data, automatic vowelization using a flat-start approach, use of a large vocabulary with 617K words and 2 million pronunciations and lastly, a system architecture based on cross-adaptation between unvowelized and vowelized acoustic models.
BibTeX
@inproceedings{soltau2007ibm,
  author = {Hagen Soltau and George Saon and Brian Kingsbury and Hong-Kwang Jeff Kuo and Lidia Mangu and Daniel Povey and Geoffrey Zweig},
  title = {{The IBM 2006 Gale Arabic ASR System}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2007},
  url = {https://openreview.net/forum?id=S5bDWCCUg5},
}

Loading related content...

Figure