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

James Christie, Dan Ellis, Eric Fosler-Lussier, Yoshihiko Gotoh, Brian Kingsbury, Nelson Morgan, Steve Renals, Tony Robinson, Gethin Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationProceedings of the 1999 DARPA Broadcast News Workshop
Publication statusPublished - 1999
EventDARPA Broadcast News Workshop - Hilton at Washington Dulles Airport, Herndon, VA, United States
Duration: 28 Feb 19993 Mar 1999

Workshop

WorkshopDARPA Broadcast News Workshop
Country/TerritoryUnited States
CityHerndon, VA
Period28/02/993/03/99

Fingerprint

Dive into the research topics of 'An Overview of the SPRACH System for the Transcription of Broadcast News'. Together they form a unique fingerprint.

Cite this