1. •Hill Climbing on Speech Lattices [COMING SOON] : C++ source code for applying hill climbing rescoring algorithm to speech word-lattices. The code is based on Google OpenFst code. The details of the algorithm can be found in the following paper: ( We are in the process of publishing the extended version of the algorithm)
   

2. 
   

3. A. Rastrow, M. Dreyer, A. Sethy, S. Khudanpur, B. Ramabhadran and M. Dredze ”Hill Climbing on Speech Lattices: A New Rescoring Framework”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2011. [paper | slides]
   

4. 
   

I am a Ph.D. candidate at the Center for Language and Speech Processing in the Electrical and Computer Engineering Department at the Johns Hopkins University. I am also affiliated with the Human Language Technology Center of Excellence (HLTCOE). My research advisor is Frederick Jelinek.

My CV in PDF format.

1. ✦  ASRU                         December 11th-16th 2011
   

2. ✦NAACL-HLT              June 1st-6th 2010 
   

3. ✦ICASSP                     March 15th-19th 2010
   

1. •Our paper got accepted to “ACL 2012”
   

2. •I have been awarded “The Frederick Jelinek Fellowship”
   

3. •Our papers got accepted to ASRU workshop!

A. Rastrow, M. Dredze, S. Khudanpur “Fast Syntactic Analysis for Statistical Language Modeling via Substructure Sharing and Uptraining”, The 50th Annual Meeting of Association for Computational Linguistics (ACL), 2012 (accepted).

A. Rastrow, M. Dredze, S. Khudanpur “Efficient Discriminative Training of Long-span Language Models”, IEEE Automatic Speech Recognition and Understanding (ASRU) Workshop, 2011.

A. Rastrow, M. Dredze, S. Khudanpur “Adapting n-gram Maximum Entropy Language Models with Conditional Entropy Regularization”, IEEE Automatic Speech Recognition and Understanding (ASRU) Workshop, 2011.

 

A. Rastrow, M. Dreyer, A. Sethy, S. Khudanpur, B. Ramabhadran and M. Dredze ”Hill Climbing on Speech Lattices: A New Rescoring Framework”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2011. [paper | slides]

 

G. Kurata, A. Sethy, B. Ramabhadran, A. Rastrow, N. Itoh and M. Nishimura ”Acoustically discrim- inative language model training with pseudo-hypothesis”, Speech Communication, Volume 5, Issue 2, pages 219-228, 2011.

C. Parada, M. Dredze, A. Sethy, and A. Rastrow. ”Learning Sub-Word Units for Open Vocabulary Speech Recognition” ACL, 2011.

A. Rastrow, F. Jelinek, A. Sethy, B. Ramabhadran ”Unsupervised Model Adaptation using Information-Theoretic Criterion”, North American Chapter of the Association for Computational Linguistics (NAACL), June 2010. [paper | slides]

D. Povey, L. Burget, et al. ”Subspace Gaussian Mixture Models - A Structured Model for Speech Recognition”, Computer Speech and Language.

A. Goshal, D. Povey, et al. ”A Novel Estimation of Feature-space MLLR for Full- Covarinace Models”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2010.

L. Burget, P. Schwarz, et. al. ”Multilingual Acoustic Modeling for Speech Recognition based on Subspace Gaussian Mixture Models”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2010.

D. Povey, L. Burget, et al. ”Subspace Gaussian Mixture Models for Speech Recognition”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2010.

N. Goel, S. Thomas, et al. ”Approaches to Automatic Lexicon Learning with Limited Training Examples”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2010.

A. Rastrow, A. Sethy, B. Ramabhadran “Constrained Discriminative Training of N-gram Language Models”, IEEE Automatic Speech Recognition and Understanding (ASRU)  Workshop,  December 2009. [paper | poster]

A. Rastrow, A. Sethy, B. Ramabhadran, F. Jelinek ”Towards Using Hybrid Word and Fragment Units for Vocabulary Independent LVCSR Systems”, In Proceedings of INTERSPEECH, September 2009. [paper | slides]

C. M. White, A. Rastrow, S. Khudanpur, F. Jelinek ”Unsupervised Estimation of the Language Model Scaling Factor”, In Proceedings of INTERSPEECH, September 2009. [paper]

A. Rastrow, A. Sethy, B. Ramabhadran, ”A New Method For OOV Detection Using Hybrid Word/Fragment System”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2009. [paper | slides]

L. Burget, P. Schwarz, P. Matejka, M. Hannemann, A. Rastrow, C. White, S. Khudanpur, H. Hermansky, J. Cernocky, ”Combination of Strongly and Weakly Constrained Recognizers for Reliable Detection of OOVs”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2008. [paper]

1. •Ph.D. Candidate, Electrical and Computer Engineering,                                                                            
   

2. Johns Hopkins University, Baltimore, MD
   

3. Advisor: Frederick Jelinek (deceased)                               September 2006-Present
   

4. Expected graduation data: May 2012
   

1. •M.S.E. Electrical and Computer Engineering, 
   

2. Johns Hopkins University, Baltimore, MD                           May 2007
   

1. •B.Sc. Electrical Engineering and Computer Engineering,
   

2. Sharif University of Technology, Tehran, IRAN                  August 2006