Aditya Malik, Nalini Ratha, et al.
CAI 2024
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. © 2011 IEEE.
Aditya Malik, Nalini Ratha, et al.
CAI 2024
Leonid Karlinsky, Joseph Shtok, et al.
CVPR 2019
Erik Altman, Jovan Blanusa, et al.
NeurIPS 2023
Pavel Klavík, A. Cristiano I. Malossi, et al.
Philos. Trans. R. Soc. A