CUED Publications database

Transcription of multi-genre media archives using out-of-domain data

Bell, PJ and Gales, MJF and Lanchantin, P and Liu, X and Long, Y and Renals, S and Swietojanski, P and Woodland, PC (2012) Transcription of multi-genre media archives using out-of-domain data. 2012 IEEE Workshop on Spoken Language Technology, SLT 2012 - Proceedings. pp. 324-329.

Full text not available from this repository.

Abstract

We describe our work on developing a speech recognition system for multi-genre media archives. The high diversity of the data makes this a challenging recognition task, which may benefit from systems trained on a combination of in-domain and out-of-domain data. Working with tandem HMMs, we present Multi-level Adaptive Networks (MLAN), a novel technique for incorporating information from out-of-domain posterior features using deep neural networks. We show that it provides a substantial reduction in WER over other systems, with relative WER reductions of 15% over a PLP baseline, 9% over in-domain tandem features and 8% over the best out-of-domain tandem features. © 2012 IEEE.

Item Type: Article
Uncontrolled Keywords: cross-domain adaptation media archives speech recognition tandem
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:08
Last Modified: 08 Dec 2014 02:27
DOI: 10.1109/SLT.2012.6424244