I am a member of the Speech and Hearing Group
at the Department of Computer Science,
University of Sheffield and is mostly working
on large scale systems for speech and language processsing using machine learning.
Open positions
If you are interested in pursuing a PhD in speech processing
please CONTACT ME.
You can find potential topical areas here.
New RA positions!
- We are looking for on RA to work on language learner assessement(more info here)
-
We will announca an RA post to work on meeting recognition and analysis shortly ....
News
|
July, 2012
|
Paper to appear in IEEE Transactions on Audio, Speech and Language Processing:
Correctness-adjusted unsupervised discriminative acoustic model adaptation.
|
|
June, 2012
|
Yulan Liu joined us to work on environment models for speech recognition.
|
|
June, 2012
|
The U-Star consortium presents its Iphone App at a press conference. We are
working on UK English Speech recognition !
press release.
The link to the app will follow !
|
|
June, 2012
|
We will be present at Interspeech with 4 papers: On Diacritisation, syllabification,
recognition for dysarthria and domain adaptation.
|
|
June, 2012
|
We will work on language learning in collaboration with a Dutch
language learning company - a new job ad will come out soon.
|
|
May, 2012
|
New EU project DocuMeet with partners in Spain, Portugal, Switzerland. .
|
|
Nov 1, 2011
|
3 Studentships and one Postdoc position available on the NST project
|
| July 5, 2011 |
T. Hain, L. Burget, J. Dines, P. N. Garner, F. Grezl, A. el Hannani, M. Huijbregts, M. Karafiat, M. Lincoln & V. Wan (2011) . Transcribing meetings with the AMIDA systems. To appear in Proc. IEEE Transactions on Audio, Speech and Language Processing
|
| July 4, 2011 |
EPSRC programme grant on
natural speech technology is kiccking off !
|
| June 1, 2011 |
We will be at Interspeech with 6 papers on far field recognition, Arabic conversational speech, multilingual
recognition and webAsR.
|
| |
twitter.com/thomashain
|
Current funded projects
-
- Natural Speech Technology (NST) is an EPSRC Programme Grant with the aim of significantly advancing the state-of-the-art in speech technology by making it more natural, approaching human levels of reliability, adaptability and conversational richness. It is a joint project with the Univ. of Edinburgh and the Univ. of Cambridge.
Domain adaptation - Matt Gibson, work Supported by Cisco
A Joint Model of Spoken Langauge Translation - Joint with Trevor Cohn, supported by Google
U-STAR - A speech translation platform
Language learning tools - Joine with itslanguage Ltd.
- Davide Marino, working on far field speech recognition.
- Network of excellence in machine learning
|
