Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Anatomy of an Extremely Fast LVCSR Decoder

George Saon, Daniel Povey, Geoffrey Zweig

IBM T.J. Watson Research Center, Yorktown Heights, NY, USA

We report in detail the decoding strategy that we used for the past two Darpa Rich Transcription evaluations (RT'03 and RT'04) which is based on finite state automata (FSA). We discuss the format of the static decoding graphs, the particulars of our Viterbi implementation, the lattice generation and the likelihood evaluation. This paper is intended to familiarize the reader with some of the design issues encountered when building an FSA decoder. Experimental results are given on the EARS database (English conversational telephone speech) with emphasis on our faster than real-time system.

Full Paper

Bibliographic reference.  Saon, George / Povey, Daniel / Zweig, Geoffrey (2005): "Anatomy of an extremely fast LVCSR decoder", In INTERSPEECH-2005, 549-552.