*********************************************************************
**************************** Special Date *****************************
*********************************************************************
Seminar
Department of Systems Engineering and Engineering Management
The
-----------------------------------------------------------------------------------------------
Title: Unsupervised discriminative training
Speaker: Dr. Lan Wang
Machine Intelligence Laboratory
Cambridge University Engineering Department(CUED)
Date : November 27th, 2006 (Monday)
Time : 4:30p.m. - 5:30p.m.
Venue : Room 513
CUHK
----------------------------------------------------------------------------------------------
Abstract:
A significant cost in obtaining acoustic training data is the
generation of accurate transcriptions. For some sources, closed-caption
data is available. This allows the use of lightly-supervised
training techniques. However, for some sources and languages,
closed-caption is not available. In these cases, unsupervised training
techniques must be used. This work examines the use of unsupervised
discriminative training. In unsupervised training, automatic
transcriptions from a recognition system are used fir training.
As these transcriptions may be erroneous, data selection may be useful.
Two forms of selection are described, one to remove non-target
language shows, the other to remove segments with low confidence.
Experiments were carried out on a Mandarin transcription task.
Results show that the gains from unsupervised training are highly
dependent on the accuracy of the automatic transcription.
----------------------------------------------------------------------------------------------
Biography:
Dr. Lan Wang is a Research Associate in the Machine
Intelligence Laboratory, Cambridge University Engineering Department
(CUED). She is working on the Autonomous Global Integrated Language
Exploitation project funded under DARPA's Global Autonomous Language
Exploitation program. She got her
master degree from
(PKU) in 1996 and worked in PKU as a lecture for five years. From October
2001, she worked on Ph.D in Computer Speech and Language Processing at
CUED. She completed her Ph.D thesis on discriminative adaptive training and
adaptation in 2005 under the supervision of Prof. Phil. Woodland. Her
interests in speech research include speech recognition and biometrics
authentication.
*********************** ALL ARE WELCOME ************************
Enquiries: Peixiang Zhao or Jeffrey Xu Yu,
Department of Systems Engineering and Engineering Management
CUHK
Website: http://www.se.cuhk.edu.hk/~seg5810
Email: seg5810@se.cuhk.edu.hk
********************************************************************