Title :
The IBM 2011 GALE Arabic speech transcription system
Author :
Mangu, Lidia ; Kuo, Hong-Kwang ; Chu, Stephen ; Kingsbury, Brian ; Saon, George ; Soltau, Hagen ; Biadsy, Fadi
Author_Institution :
IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
We describe the Arabic broadcast transcription system fielded by IBM in the GALE Phase 5 machine translation evaluation. Key advances over our Phase 4 system include a new Bayesian Sensing HMM acoustic model; multistream neural network features; a MADA vowelized acoustic model; and the use of a variety of language model techniques with significant additive gains. These advances were instrumental in achieving a word error rate of 7.4% on the Phase 5 evaluation set, and an absolute improvement of 0.9% word error rate over our 2009 system on the unsequestered Phase 4 evaluation data.
Keywords :
Bayes methods; hidden Markov models; neural nets; speech processing; Bayesian sensing HMM acoustic model; GALE Phase 5 machine translation evaluation; IBM 2011 GALE Arabic speech transcription system; MADA vowelized acoustic model; language model techniques; multistream neural network features; phase 4 system; unsequestered phase 4 evaluation data; Acoustics; Computational modeling; Dictionaries; Hidden Markov models; Lattices; Training; Transforms; large vocabulary speech recognition;
Conference_Titel :
Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on
Conference_Location :
Waikoloa, HI
Print_ISBN :
978-1-4673-0365-1
Electronic_ISBN :
978-1-4673-0366-8
DOI :
10.1109/ASRU.2011.6163943
