Publications

Book & Book Chapters:

1. Amarnag Subramanya and Partha Pratim Talukdar, "Graph-based Semi-Supervised Learning", Morgan & Claypool, 2014.

2. Jeff Bilmes and Amarnag Subramanya, "Large-scale Semi-supervised learning", in Scaling Up Machine Learning, Editors Ron Bekkerman, Misha Bilenko and John Langford, Cambridge University Press.

Journals:

1. Nevena Lazic, Amarnag Subamanya, Michael Ringgaard, and Fernando Pereira, "Plato: A Selective Context Model for Entity Resolution", Transactions of the Association of Computational Linguistics (TACL), 2015.

2. Amarnag Subramanya and Jeff Bilmes, "Semi-supervised learning with Measure Propagation", Journal of Machine Learning Research (JMLR), Volume 12, December 2011.

3. Amarnag Subramanya, Zhengyou Zhang, Zicheng Liu and Alex Acero, "Multisensory Processing for Speech Enhancement and Magnitude-Normalized Spectra for Speech Modeling", Speech Communication, Volume 50, Issue 3, March 2008.

4. Amarnag Subramanya, Mike Seltzer and Alex Acero, "Automatic Removal of Types Keystrokes from Speech Signals", IEEE Signal Processing Letters, Volume 14, Number 5, May 2007.

5. Stan Birchfield and Amarnag Subramanya, "Microphone Array Position Calibration by Basis-Point Classical Multidimensional Scaling", IEEE Transactions on Speech and Audio Processing, Volume 13, Number 5, September 2005.

Refereed Conferences:

1. Dan Gillick, Cliff Brunk, Oriol Vinyals, Amarnag Subramanya, "Multilingual Language Processing from Bytes", North American Chapter of the Association of Computational Linguistics: Human Language Technologies (NAACL HLT) 2016 (to appear). See here for arXiv version.

2. Ni Lao, Amarnag Subramanya, Fernando Pereira and William Cohen, "Reading the Web with Learned Syntactic-Semantic Inference Rules", Empirical Methods in Natural Language Processing (EMNLP), 2012.

3. Sameer Singh, Amarnag Subramanya, Fernando Pereira and Andrew McCallum, "Large-Scale Cross-Document Coreference Using Distributed Inference and Hierarchical Models", Association for Computational Linguistics (ACL), Portland, Oregon, 2011.

4. Sameer Singh, Amarnag Subramanya, Fernando Pereira and Andrew McCallum, "Distributed MAP Inference for Undirected Graphical Models", Neural Information Processing Society (NIPS), Workshop on Learning on Cores, Clusters and Clouds (LCCC), 2010.

5. Amarnag Subramanya, Slav Petrov and Fernando Pereira, "Efficient Graph-Based Semi-Supervised Learning of Structured Tagging Models", Empirical Methods in Natural Language Processing (EMNLP), Boston, Massachusetts, 2010.

6. Amarnag Subramanya and Jeff Bilmes, "Entropic Graph Regularization in Non-Parametric Semi-Supervised Classification", Neural Information Processing Society (NIPS), Vancouver, Canada, December, 2009.

7. Amarnag Subramanya and Jeff Bilmes, "Large-Scale Graph-based Transductive Inference", Workshop on Large-Scale Machine Learning: Parallelism and Massive Datasets at Neural Information Processing Society (NIPS), Vancouver, Canada, December, 2009.

8. Amarnag Subramanya and Jeff Bilmes, "The Semi-Supervised Switchboard Transcription Project", INTERSPEECH, Brighton, UK, 2009.

9. Jon Malkin, Amarnag Subramanya and Jeff Bilmes, " On the Semi-Supervised Learning of Multi-Layered Perceptrons", INTERSPEECH, Brighton, UK, 2009 (Best Student Paper Award).

10. Amarnag Subramanya and Jeff Bilmes, "Soft-Supervised Text Classification", Empirical Methods in Natural Language Processing (EMNLP), Hawaii, 2008.

11. Amarnag Subramanya and Jeff Bilmes, "Applications of Virtual-Evidence based Speech Recognizer Training", INTERSPEECH, Brisbane, Australia, 2008.

12. Amarnag Subramanya, Chris Bartels, Jeff Bilmes and Patrick Nguyen, "Uncertainty in training Large Vocabulary Speech Recognizers", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Japan, 2007.

13. Amarnag Subramanya and Jeff Bilmes, "Virtual Evidence for Training Speech Recognizers using Partially Labeled Data", Human Language Technology Conference --- North American Association for Computational Lingustics (NAACL-HLT07), Rochester, NY, 2007.

14. Amarnag Subramanya, Zhengyou Zhang, Arun Surendran, Patrick Nguyen, Mukund Narasimhan and Alex Acero, "A Generative-Discriminative Framework using Ensemble Methods for Text-Dependant Speaker Verification", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hawaii, 2007.

15. Amarnag Subramanya, Alvin Raj, Jeff Bilmes and Dieter Fox, "Hierarchical Models for Activity Recognition", IEEE International Workshop in Multimedia Signal Processing (MMSP), Victoria, BC, Canada, October, 2006.

16. Amarnag Subramanya, Mike Seltzer and Alex Acero, "Automatic Removal of Typed Keystrokes from Speech Signals", International Conference on Spoken Language Processing (ICSLP), Pittsburgh, PA, September 2006.

17. Amarnag Subramanya, Alvin Raj, Jeff Bilmes and Dieter Fox, "Recognizing Activities and Spatial Context Using Wearable Sensors", 21st Conference on Uncertainty in Artificial Intelligence (UAI06) , Cambridge, MA, July, 2006.

18. Alvin Raj, Amarnag Subramanya, Dieter Fox and Jeff Bilmes, "Rao-Blackwellized Particle Filters for Recognizing Activities and Spatial Context Using Wearable Sensors", International Symposium on Experimental Robotics (ISER) Rio de Janeiro, Brazil, July 2006.

19. Amarnag Subramanya, Zhengyou Zhang, Zicheng Liu, and Alex Acero, "Speech Modeling with Magnitude-Normalized Complex Spectra and its Application to Multisensory Speech Enhancement", IEEE International Conference on Multimedia and Expo (ICME), 2006.

20. Amarnag Subramanya, Zhengyou Zhang, Zicheng Liu, Jasha Droppo and Alex Acero, "A graphical model for Multi-Sensory Speech Processing in Air-and-Bone Conductive Microphones", European Conference on Speech Communication and Technology (EUROSPEECH), September 2005.

21. Amarnag Subramanya, Jeff Bilmes and Chia-Ping Chen, "Focused Word Segmentation for ASR", European Conference on Speech Communication and Technology (EUROSPEECH), September 2005.

22. Amarnag Subramanya, Li Deng, Zicheng Liu and Zhengyou Zhang, "Multi-Sensory Speech Processing: Incorporating Automatically Extracted Hidden Dynamic Information", IEEE International Conference on Multimedia and Expo (ICME), Amsterdam, 2005.

23. Zicheng Liu, Amarnag Subramanya, Zhengyou Zhang, Jasha Droppo and Alex Acero, "Leakage Model and Teeth Clack removal for Air-and-Bone Conductive Integrated Microphones", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Philadelphia, 2005.

24. Amarnag Subramanya, Stan Birchfield, "Extension and Evaluation of MDS for Geometric Microphone Array Calibration", European Signal Processing Conference, Vienna (EUSIPCO), Austria, 2004.

25. Amarnag Subramanya, John Gowdy, Chris Bartels, Jeff Bilmes, "DBN Based Multi-Stream Models for Audio-Visual Speech Recognition", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Montreal, 2004.

26. Amarnag Subramanya, Raghunandan Kumaran, John Gowdy, "Real time Eye tracking for Human Computer Interfaces", IEEE International Conference on Multimedia and Expo (ICME), Baltimore, 2003.

    1. Amarnag Subramanya, Eric Patterson, Sabri Gurbuz, John Gowdy, "Audio-Visual Speech Intergration using Coupled Hidden Markov Models for continuous Speech Recognition", IEEE International Conference on Acoustics, Speech and Signal Processing, Hong Kong, 2003.

Thesis:

1. Amarnag Subramanya, "Soft-Supervised Learning", PhD Thesis, University of Washington, Seattle, 2009.

   1. Amarnag Subramanya, "Graphical Models for Audio-Visual Speech Recognition", Masters Thesis, Clemson University, 2004.

Technical Reports:

1. Jon Malkin, Amarnag Subramanya and Jeff Bilmes, " On the Semi-Supervised Learning of Multi-Layered Perceptrons", Technical Report UWEETR-2009-0003, University of Washington, Dept. of EE, 2009.

2. Amarnag Subramanya, Zhengyou Zhang, Zicheng Liu, and Alex Acero, "Speech Modeling with Magnitude-Normalized Complex Spectra and its Application to Multisensory Speech Enhancement", Microsoft Research Technical Report, MSR-TR-2005-126, September 2005.