The UEDIN ASR Systems for the IWSLT 2014 Evaluation

Peter Bell, Pawel Swietojanski, Joris Driesen, Mark Sinclair, Fergus McInnes, Steve Renals

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

Abstract / Description of output

This paper describes the University of Edinburgh (UEDIN) ASR systems for the 2014 IWSLT Evaluation. Notable features of the English system include deep neural network acoustic models in both tandem and hybrid configuration with the use of multi-level adaptive networks, LHUC adaptation and Maxout units. The German system includes lightly supervised training and a new method for dictionary generation. Our voice activity detection system now uses a semi-Markov model to incorporate a prior on utterance lengths. There are improvements of up to 30% relative WER on the tst2013 English test set.
Original languageEnglish
Title of host publication11th International Workshop on Spoken Language Translation (IWSLT 2014)
Number of pages8
Publication statusPublished - 2014


Dive into the research topics of 'The UEDIN ASR Systems for the IWSLT 2014 Evaluation'. Together they form a unique fingerprint.

Cite this