Post-doc opportunity at TTI-Chicago
A post-doc position at the intersection of speech recognition and machine learning is available. The starting point for this post-doc is our ongoing work on multi-view learning of speech representations, described in part in the publications below. There are a number of possible future directions that can be pursued, depending on the interests of the post-doc.
The main duties of the post-doc will be his/her research activities in collaboration with me and other potential collaborators on this work (currently this includes researchers at U. Washington, Johns Hopkins U., U. Edinburgh, and TTIC). Teaching and advising opportunities are also likely to be available if desired.
There are no citizenship requirements for the post-doc. The position will remain open until filled. For more information or to apply, please email Karen Livescu at klivescu@ttic.edu.
Related publications/preprints:
W. Wang, R. Arora, K. Livescu, and J. Bilmes
"On deep multi-view representation learning: Objectives and Optimization"
arXiv:1602.01024 (long version of ICML 2015 paper)
(code)
T. Michaeli, W. Wang, and K. Livescu
"Nonparametric canonical correlation analysis"
arXiv:1511.04839
W. Wang and K. Livescu
"Large-scale approximate kernel canonical correlation analysis"
arXiv:1511.04773 (to appear at ICLR 2016)
H. Kamper, W. Wang, and K. Livescu
"Deep convolutional acoustic word embeddings using word-pair side information"
arXiv:1507.06073 (to appear at ICASSP 2016)
W. Wang, R. Arora, N. Srebro, and K. Livescu
"Stochastic optimization for deep CCA via nonlinear orthogonal iterations"
53th Annual Allerton Conference on Communication, Control, and Computing, 2015.
W. Wang, R. Arora, K. Livescu, and J. Bilmes
"On deep multi-view representation learning"
ICML 2015.
(code)
A. Lu, W. Wang, M. Bansal, K. Gimpel, and K. Livescu
"Deep multilingual correlation for improved word embeddings"
NAACL 2015.
W. Wang, R. Arora, K. Livescu, and J. Bilmes
"Unsupervised learning of acoustic features via deep canonical correlation analysis"
ICASSP 2015.
(code)
R. Arora and K. Livescu
"Multi-view learning with supervision for transformed bottleneck features"
ICASSP 2014.
G. Andrew, R. Arora, J. Bilmes, and K. Livescu
"Deep canonical correlation analysis"
ICML 2013.
R. Arora and K. Livescu
"Multi-view CCA-based acoustic features for phonetic recognition across speakers and domains"
ICASSP 2013.
R. Arora, A. Cotter, K. Livescu, and N. Srebro
"Stochastic optimization for PCA and PLS"
50th Annual Allerton Conference on Communication, Control, and Computing, 2012.
R. Arora and K. Livescu
"Kernel CCA for multi-view learning of acoustic features using articulatory measurements"
Symposium on Machine Learning in Speech and Language Processing (MLSLP) 2012.
S. Bharadwaj, R. Arora, K. Livescu, and M. Hasegawa-Johnson
"Multi-view acoustic feature learning using articulatory measurements"
IEEE International Workshop on Statistical Machine Learning for Speech Processing (IWSML) 2012.
K. Livescu and M. Stoehr
"Multi-view learning of acoustic features for speaker recognition"
ASRU 2009.
K. Chaudhuri, S. Kakade, K. Livescu, and K. Sridharan
"Multi-view clustering via canonical correlation analysis"
ICML 2009.