The IBM 2009 GALE Arabic speech transcription system

We describe the Arabic broadcast transcription system elded by IBM in the GALE Phase 4 machine translation evaluation. Key advances over our Phase 3.5 system include improvements to contextdependent modeling in vowelized Arabic acoustic models; the use of neural-network features provided by the International Computer Science Institute; Model M language models; a neural network language model that uses syntactic and morphological features; and improvements to our system combination strategy. These advances were instrumental in achieving a word error rate of 8.9% on the

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Brian Kingsbury, Hagen Soltau, George Saon, Stephen M. Chu, Hong-Kwang Kuo, Lidia Mangu, Suman V. Ravuri, Nelson Morgan, Adam Janin
• Keywords: Arabic Acoustic Models, ICASSP 2011, International Computer Science Institute, Language Model, Signal Processing