T
Thomas Hain
Researcher at University of Sheffield
Publications - 211
Citations - 5274
Thomas Hain is an academic researcher from University of Sheffield. The author has contributed to research in topics: Word error rate & Transcription (software). The author has an hindex of 35, co-authored 200 publications receiving 4725 citations. Previous affiliations of Thomas Hain include University of Cambridge & RWTH Aachen University.
Papers
More filters
Book ChapterDOI
The AMI meeting corpus: a pre-announcement
Jean Carletta,Simone Ashby,Sebastien Bourban,Michael J. Flynn,Maël Guillemot,Thomas Hain,Jaroslav Kadlec,Vasilis Karaiskos,Wessel Kraaij,Melissa Kronenthal,Guillaume Lathoud,Mike Lincoln,Agnes Lisowska,Iain McCowan,Wilfried Post,Dennis Reidsma,Pierre Wellner +16 more
TL;DR: The AMI Meeting Corpus as mentioned in this paper is a multi-modal data set consisting of 100 hours of meeting recordings, which is being created in the context of a project that is developing meeting browsing technology and will eventually be released publicly.
The AMI meeting corpus
Iain McCowan,Jean Carletta,Wessel Kraaij,Simone Ashby,S. Bourban,Michael J. Flynn,Maël Guillemot,Thomas Hain,J. Kadlec,Vasilis Karaiskos,Melissa Kronenthal,Guillaume Lathoud,Mike Lincoln,Agnes Lisowska,Wilfried Post,Dennis Reidsma,Pierre Wellner +16 more
TL;DR: The corpus is being distributed using a web server designed to allow convenient browsing and download of multimedia content and associated annotations, as well as data collection, annotation and distribution.
Proceedings ArticleDOI
Recognition and understanding of meetings the AMI and AMIDA projects
TL;DR: An overview of the AMI and AMIDA projects, with an emphasis on speech recognition and content extraction, is presented.
Proceedings Article
Hypothesis spaces for minimum Bayes risk training in large vocabulary speech recognition.
Matthew Gibson,Thomas Hain +1 more
TL;DR: The Minimum Bayes Risk framework has been a successful strategy for the training of hidden Markov models for large vocabulary speech recognition but use of phoneme-based criteria appears to be more successful.
Proceedings ArticleDOI
The AMI System for the Transcription of Speech in Meetings
Thomas Hain,Vincent Wan,Lukas Burget,Martin Karafiat,John Dines,Jithendra Vepa,Giulia Garau,Mike Lincoln +7 more
TL;DR: The AMI transcription system for speech in meetings developed in collaboration by five research groups includes generic techniques such as discriminative and speaker adaptive training, vocal tract length normalisation, heteroscedastic linear discriminant analysis, maximum likelihood linear regression, and phone posterior based features, as well as techniques specifically designed for meeting data.