|
|
|
Yongqiang (Eric) Wang
Eric Wang entered department of electronic engineering and information science, University of science and technology of China (USTC) in 2002. After obtaining his B.Eng degree in 2006, he pursed his M.Phil. degree ( in computer science ) at the University of Hong Kong until 2009, while he was also an intern at speech group, Microsoft Research Asia from Sept. 2007 to July 2008 and Feb. 2009 to Oct. 2009. He was also an intern at Microsoft Research, Redmond, WA from June, 2012 to Sept. 2012.
He is now a PhD student at the Machine Intelligence Laboratory, supervised by
Prof. Mark Gales. He is a
member of Darwin College in Cambridge University. [Resume]
|
Research Interests
- Machine Learning and Pattern Recognition
- Acoustic Modelling and Model Adaptation
- Robust Speech Recognition in Noisy Environment
- Handwriting Recognition
Selected Publications
- Y.-Q. Wang and M. J. F. Gales,
An explicit independence constraint for factorised adaptation in speech
recognition ,
to appear in Proc. Interspeech-2013.
August 2013, Lyon, France.
- M. L. Seltzer, D. Yu and Y.-Q. Wang,
An investigation of deep neural networks for noise robust speech recognition ,
to appear in Proc. ICASSP-2013.
May 2013, Vancouver, Canada.
- Y.-Q. Wang and M. J. F. Gales,
TANDEM system adaptation using multiple linear feature transforms ,
to appear in Proc. ICASSP-2013.
May 2013, Vancouver, Canada.
- Y.-Q. Wang and M. J. F. Gales,
Model-based approaches to adaptive training in reverberant environments ,
in Proc. Interspeech-2012.
[PDF]
[poster]
- Y.-Q. Wang and M. J. F. Gales,
Speaker and noise factorisation for robust speech recognition ,
IEEE transactions on audio, speech and language processing Vol20(7), September 2012.
[PDF]
- Y.-Q. Wang and M. J. F. Gales,
Improving reverberant VTS for hands-free robust speech recognition ,
in ASRU-2011. best student paper award shortlist
[PDF]
[poster]
- M. J. F. Gales and Y.-Q. Wang
Model-based approaches to handling additive noise in reverberant environments ,
in workshop on hands-free speech communication and microphone arrays, May 2011.
[PDF]
- Y.-Q. Wang and M. J. F. Gales,
Speaker and noise factorisation on AURORA4 task ,
in Proc. ICASSP-2011, May 2011.
[PDF]
[slides]
- Y.-Q. Wang and Q. Huo,
Building compact recognizers of handwritten Chinese characters using precision constrained Gaussian model, minimum classification error training and parameter compression ,
in International Journal on Document Analysis and Recognition, vol. 14, issue 3.
[PDF]
- Y.-Q. Wang and Q. Huo
Sample-separation-margin based minimum classification error training of pattern classifiers with quadratic discriminant functions,
in Proc. ICASSP-2010, March 2010
[PDF]
[slides](in pptx, presented by Dr. Qiang Huo)
- Y.-Q. Wang and Q. Huo
Design compact recognizers of handwritten Chinese characters using precision constrained Gaussian models, minimum classification error training and parameter compression,
in Proc. ICDAR-2009 Winner of best industry related paper
[PDF]
[slides](in pptx, presented by Dr. Qiang Huo)
Contact Information
Yongqiang Wang
Machine Intelligence Laboratory
Cambridge University Engineering Department
Trumpington Street, Cambridge CB2 1PZ, UK
Email: yw293 (at sign) cam.ac.uk
|
|
|
