The IBM 2008 GALE Arabic speech transcription system

This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system include improved discriminative training, the use of Subspace Gaussian Mixture Models (SGMM), neural network acoustic features, variable frame rate decoding, training data partitioning experiments, unpruned n-gram language models and neural network language models. These advances were instrumental in achieving a word error rate of 8.9% on the evaluation test set.

• Type: Conference
• Year: 2010
• Where: ICASSP
• Authors: George Saon, Hagen Soltau, Upendra Chaudhari, Stephen M. Chu, Brian Kingsbury, Hong-Kwang Kuo, Lidia Mangu, Daniel Povey
• Keywords: ICASSP 2010, Language Models, Neural Network, Phase 3.5 Machine, Signal Processing