CAST Speech-to-Speech Translation

Mailing address:
AI Center
SRI International
333 Ravenswood Avenue
Menlo Park, CA 94025-3493

AIC Program:  Natural Language

SRI’s CAST project, part of the DARPA CAST program, has developed a prototype limited-domain speech-to-speech translator between English and Pashto. Our pincipal translation component uses SRI’s Gemini natural language parser and associated generator. The speech recognition engine is DynaSpeak. This project is joint work with Kristin Precoda and Horacio Franco of SRI’s STAR lab.

• Fry, John. Assembling a Parallel Corpus from RSS News Feeds, in Proceedings of the Workshop on Example-Based Machine Translation, MT Summit X, Phuket, Thailand, September 2005.  [PDF, Details]

• Kathol A. and Precoda, K. and Vergyri, D. and Wang, W. and Riehemann, S. Speech Translation for Low-Resource Languages: The Case of Pashto, in Eurospeech 2005, 2005.  [PDF, Details]

• Belvin, R. and Riehemann, S. and Precoda, K. A Fine-Grained Evaluation Method for Speech-to-Speech Machine Translation Using Concept Annotations, in LREC 2004, 2004.  [PDF, Details]

• Precoda, K. and Culy, C. and Franco, H. and Dost, A. and Frandsen, M. and Fry, J. and Kathol A. and Richey, C. and Riehemann, S. and Vergyri, D. and Zheng, J. Limited-Domain Speech-to-Speech Translation between English and Pashto, in HLT/NAACL Demo Sessions, May 2004.  [PDF, Details]

• Culy, C. and Riehemann, S. Z. The Limits of N-Gram Translation Evaluation Metrics, in Proceedings of MT Summit IX (to appear), 2003.  [PDF, Details]

©2013 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy