An Overview of the SPRACH System for the Transcription of Broadcast News

Articles:

Title:: An Overview of the SPRACH System for the Transcription of Broadcast News
Author(s):: Cook, Gary
Christie, James
Ellis, Daniel P. W.
Fosler-Lussier, Eric
Gotoh, Yoshi
Kingsbury, Brian
Morgan, Nelson
Renals, Steve
Robinson, Tony
Williams, Gethin
Date:: 1999
Type:: Articles
Department:: Electrical Engineering
Permanent URL:: http://hdl.handle.net/10022/AC:P:13837
Book/Journal Title:: Proceedings of the DARPA Broadcast News Workshop, February 28-March 3, 1999, Hilton at Washington Dulles Airport, Herndon, Virginia
Publisher:: Information Technology Laboratory, National Institute of Standards and Technology
Publisher Location:: Gaithersburg, MD
Abstract:: This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and multi-layer perceptron acoustic models. We describe both a system designed for the primary transcription hub, and a system for the less-than 10 times real-time spoke. We then describe recent developments to CHRONOS, a time-first stack decoder. We show how these developments have simplified the evaluation system, and led to significant reductions in the error rate of the 10x real-time system. We also present a system designed to operate in real-time with negligible search error.
Subject(s):: Electrical engineering
Artificial intelligence