Peder A. Olsen  Peder A. Olsen photo       

contact information

Research Staff Member
Thomas J. Watson Research Center, Yorktown Heights, NY USA
  +1dash914dash945dash3772

links

Professional Associations

Professional Associations:  American Mathematical Society (AMS)  |  IEEE   |  Mathematical Association of America  |  Society for Industrial and Applied Mathematics

more information

More information:  Speech Separation


2012

Newton-Like Methods for Sparse Inverse Covariance Estimation
P.A. Olsen, F. Oztoprak, J. Nocedal, S.J. Rennie
2012 - optimization-online.org

Hidden Markov acoustic modeling with bootstrap and restructuring for low-resourced languages
Xiaodong Cui, Jian Xue, Xin Chen, Peder A Olsen, Pierre L Dognin, Upendra V Chaudhari, John R Hershey, Bowen Zhou
Audio, Speech, and Language Processing, IEEE Transactions on 20(8), 2252--2264, IEEE, 2012

Efficient Automatic Differentiation of Matrix Functions
P.A. Olsen, S.J. Rennie, V. Goel
Recent Advances in Algorithmic Differentiation, 71--81, Springer, 2012


2011

Rapid feature space MLLR speaker adaptation with bilinear models
S. Zhang, P.A. Olsen, Y. Qin
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 4452--4455

Discriminative training for full covariance models
P.A. Olsen, V. Goel, S.J. Rennie
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 5312--5315

A-Functions: A generalization of Extended Baum-Welch transformations to convex optimization
D. Kanevsky, D. Nahamoo, T.N. Sainath, B. Ramabhadran, P.A. Olsen
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 5164--5167

Acoustic modeling with bootstrap and restructuring based on full covariance
Xiaodong Cui, Xin Chen, Jian Xue, Peder A Olsen, John R Hershey, Bowen Zhou
INTERSPEECH, pp. 1697--1700, 2011

Sparse Maximum A Posteriori Adaptation
P.A. Olsen, J. Huang, V. Goel, S.J. Rennie
2011 - ieeexplore.ieee.org

Clustering of bootstrapped acoustic model with full covariance
Xin Chen, Xiaodong Cui, Jian Xue, Peder Olsen, John Hershey, Bowen Zhou, Yunxin Zhao
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 4496--4499


2010

Modeling Posterior Probabilities using the Linear Exponential Family
P. Olsen, V. Goel, C. Micchelli, J.R. Hershey
Eleventh Annual Conference of the International Speech Communication Association, 2010

Restructuring Exponential Family Mixture Models
P.L. Dognin, J.R. Hershey, V. Goel, P. Olsen
Eleventh Annual Conference of the International Speech Communication Association, 2010

Single-channel multitalker speech recognition
S.J. Rennie, J.R. Hershey, P.A. Olsen
Signal Processing Magazine, IEEE 27(6), 66--80, IEEE, 2010

Restructuring acoustic models for client and server-based automatic speech recognition,”
P.L. Dognin, J.R. Hershey, V. Goel, P.A. Olsen
Eleventh Annual Conference of the International Speech Communication Association, 2010


Incorporating sparse representation phone identification features in automatic speech recognition using exponential families
V. Goel, T.N. Sainath, B. Ramabhadran, P. Olsen, D. Nahamoo, D. Kanevsky
Eleventh Annual Conference of the International Speech Communication Association, 2010

Signal interaction and the devil function
J R Hershey, P A Olsen, S J Rennie
Interspeech, pp. 334-337, 2010

Super-human multi-talker speech recognition: A graphical modeling approach
J R Hershey, S J Rennie, P A Olsen, T T Kristjansson
Computer Speech & Language 24(1), 45--66, Elsevier, 2010


2009

Variational loopy belief propagation for multi-talker speech recognition
S.J. Rennie, J.R. Hershey, P.A. Olsen
Tenth Annual Conference of the International Speech Communication Association, 2009

Optimal quantization and bit allocation for compressing large discriminative feature space transforms
E. Marcheret, V. Goel, P.A. Olsen
Automatic Speech Recognition \& Understanding, 2009. ASRU 2009. IEEE Workshop on, pp. 64--69

Hierarchical Variational Loopy Belief Propagation for Multi-talker Speech Recognition
Steven J. Rennie, John R. Hershey and Peder A. Olsen
ASRU 2009, pp. 176--181


Compacting Discriminative Feature Space Transforms for Embedded Devices
E. Marcheret, J.Y. Chen, P. Fousek, P.A. Olsen, V. Goel
Tenth Annual Conference of the International Speech Communication Association, 2009

Variational loopy belief propagation for efficient multi-talker speech recognition
S J Rennie, J R Hershey, P A Olsen
Proceedings of Interspeech, 2009


Refactoring acoustic models using variational density approximation
P.L. Dognin, J.R. Hershey, V. Goel, P.A. Olsen
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on, pp. 4473--4476

Single-channel speech separation and recognition using loopy belief propagation
S.J. Rennie, J.R. Hershey, P.A. Olsen
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on, pp. 3845--3848

A fast, accurate approximation to log likelihood of Gaussian mixture models
P.L. Dognin, V. Goel, J.R. Hershey, P.A. Olsen
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on, pp. 3817--3820

Acoustic modeling using exponential families
V. Goel, P.A. Olsen
Tenth Annual Conference of the International Speech Communication Association, 2009


2008

Variational bhattacharyya divergence for hidden markov models
J.R. Hershey, P.A. Olsen
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on, pp. 4557--4560

Accelerated monte carlo for kullback-leibler divergence between gaussian mixture models
J.Y. Chen, J.R. Hershey, P.A. Olsen, E. Yashchin
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on, pp. 4553--4556

Optimizing speech recognition grammars using a measure of similarity between hidden Markov models
B Mohanty, J Hershey, P Olsen, S Kozat, V Goel
Acoustics, Speech and Signal Processing, 2008, pp. 4953--4956

Efficient model-based speech separation and denoising using non-negative subspace analysis
S.J. Rennie, J.R. Hershey, P.A. Olsen
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on, pp. 1833--1836


2007

Bhattacharyya error and divergence using variational importance sampling
P Olsen, J Hershey
Interspeech, Antwerp, Belgium (August 2007)

Single channel speech separation using factorial dynamics
J.R. Hershey, T. Kristjansson, S. Rennie, P.A. Olsen
Advances in Neural Information Processing Systems19, 593, MIT; 1998, 2007

Variational sampling approaches to word confusability
J.R. Hershey, P.A. Olsen, R.A. Gopinath
Information Theory and Applications Workshop, 2007, pp. 1--119

Variational Kullback-Leibler divergence for hidden Markov models
J.R. Hershey, P.A. Olsen, S.J. Rennie
Automatic Speech Recognition \& Understanding, 2007. ASRU. IEEE Workshop on, pp. 323--328

Approximating the Kullback Leibler divergence between Gaussian mixture models
J.R. Hershey, P.A. Olsen
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on, pp. IV--317

Word confusability-measuring hidden Markov model similarity
J.Y. Chen, P.A. Olsen, J.R. Hershey
Eighth Annual Conference of the International Speech Communication Association, 2007

Discriminative estimation of subspace constrained gaussian mixture models for speech recognition
Scott Axelrod, Vaibhava Goel, Ramesh Gopinath, Peder Olsen, Karthik Visweswariah
Audio, Speech, and Language Processing, IEEE Transactions on 15(1), 172--189, IEEE, 2007


2006

The Iroquois model: Using temporal dynamics to separate speakers
S. Rennie, P. Olsen, J. Hershey, T. Kristjansson
Workshop on Statistical and Perceptual Audio Processing (SAPA), Pittsburgh, PA, 2006

Separating multiple speakers using temporal constraints
SJ Rennie, P A Olsen, J R Hershey, TT Kristjansson
ISCA Workshop on Statistical And Perceptual Audition, 2006

Single channel speech separation using layered hidden Markov models
J Hershey, T Kristjansson, S Rennie, P Olsen
Advances in Neural Information Processing Systems (NIPS), 2006

Dynamic noise adaptation
S. Rennie, T. Kristjansson, P. Olsen, R. Gopinath
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on, pp. I--I

Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system
T. Kristjansson, J. Hershey, P. Olsen, S. Rennie, R. Gopinath
Ninth International Conference on Spoken Language Processing, pp. 97--100, 2006


2005

Subspace constrained Gaussian mixture models for speech recognition
Scott Axelrod, Vaibhava Goel, Ramesh A Gopinath, Peder A Olsen, Karthik Visweswariah
Speech and Audio Processing, IEEE Transactions on 13(6), 1144--1160, IEEE, 2005

Initializing subspace constrained Gaussian mixture models
P.A. Olsen, K. Visweswariah, R. Gopinath
Proc. of the ICASSP, pp. 661--664, 2005

Voicing features for robust speech detection
T. Kristjansson, S. Deligne, P. Olsen
Ninth European Conference on Speech Communication and Technology, pp. 3, 2005

Feature adaptation using projection of Gaussian posteriors
K. Visweswariah, P. Olsen
Ninth European Conference on Speech Communication and Technology, 2005


2004

Modeling inverse covariance matrices by basis expansion
P.A. Olsen, R.A. Gopinath
Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on, pp. 37--46, IEEE, 2004

Fast clustering of Gaussians and the virtue of representing Gaussians in exponential model format
P. Olsen, K. Visweswariah
Eighth International Conference on Spoken Language Processing, 2004


2003

Discriminative estimation of subspace precision and mean (SPAM) models.
Vaibhava Goel, Scott Axelrod, Ramesh A Gopinath, Peder A Olsen, Karthik Visweswariah
INTERSPEECH, 2003

Gaussian mixture modeling with volume preserving nonlinear feature space transforms
P.A. Olsen, S. Axelrod, K. Visweswariah, R.A. Gopinath
Automatic Speech Recognition and Understanding, 2003. ASRU'03. 2003 IEEE Workshop on, pp. 285--290

An efficient integrated gender detection scheme and time mediated averaging of gender dependent acoustic models
P.A. Olsen, S. Dharanipragada
Eighth European Conference on Speech Communication and Technology, pp. 2509--2512, 2003

Dimensional reduction, covariance modeling, and computational complexity in ASR systems
Scott Axelrod, Ramesh Gopinath, Peder Olsen, Karthik Visweswariah
Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP'03). 2003 IEEE International Conference on, pp. I--864

Maximum likelihood training of subspaces for inverse covariance modeling
Karthik Visweswariah, P Olsen, Ramesh Gopinath, Scott Axelrod
Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP'03). 2003 IEEE International Conference on, pp. I--848


2002

On an optimization problem arising from probability density estimation
S. Basu, U. Khan, CA Michelli, P. Olsen
Revista de la Real Academia de Ciencias Exactas, F\'\isicas y Naturales. Serie A: Matem\'aticas (RACSAM) 96(2), 139--156, 2002

Automatic transcription of broadcast news
SS Chen, E. Eide, MJF Gales, RA Gopinath, D. Kanvesky, P. Olsen
Speech Communication 37(1-2), 69--87, Elsevier, 2002


Theory and practice of acoustic confusability
H. Printz, P.A. Olsen
Computer Speech \& Language 16(1), 131--164, Elsevier, 2002

Modeling with a subspace constraint on inverse covariance matrices
S. Axelrod, R. Gopinath, P. Olsen
Seventh International Conference on Spoken Language Processing, 2002

A robust high accuracy speech recognition system for mobile applications
S. Deligne, S. Dharanipragada, R. Gopinath, B. Maison, P. Olsen, H. Printz
Speech and Audio Processing, IEEE Transactions on 10(8), 551--561, IEEE, 2002


2001

Determining and using acoustic confusability, acoustic perplexity and synthetic acoustic word error rate
S E Axelrod, P A Olsen, H W Printz, P V De Souza
US Patent App. 09/ ..., 2001 - Google Patents, Google Patents
US Patent App. 09/838,449

Power exponential densities for the training and classification of acoustic feature vectors in speech recognition
S. Basu, C.A. Micchelli, P. Olsen
Journal of Computational and Graphical Statistics 10(1), 158--184, ASA, 2001

Low-resource speech recognition of 500-word vocabularies
S. Deligne, E. Eide, R. Gopinath, D. Kanevsky, B. Maison, P. Olsen, H. Printz, J. Sedivy
Proceedings of the Sixth European Conference on Speech Communication and Technology, 2001

Speech recognition for DARPA communicator
Andrew Aaron, S Chen, P Cohen, Satya Dharanipragada, Ellen Eide, Martin Franz, J-M Leroux, X Luo, Beno\^\it Maison, Lidia Mangu, others
Acoustics, Speech, and Signal Processing, 2001. Proceedings.(ICASSP'01). 2001 IEEE International Conference on, pp. 489--492


2000

IBM's 10xReal-time broadcast news transciption used in the 1999 hub4 evaluation
E. Eide, B. Maison, D. Kavensky, P. Olsen, S. Chen, L. Mangu, MJF Gales, M. Novak, R. Gopinath
2000 - publications.eng.cam.ac.uk

Transcription Of Broadcast News With A Time Constraint: IBM's 10xRT HUB4 System
E. Eide, B. Maison, D. Kanevsky, P. Olsen, S. Chen, L. Mangu, M. Gales, M. Novak, R. Gopinath
Sixth International Conference on Spoken Language Processing, 2000

IBM's 10x Real-time Broadcast News Transcription System Used in the 1999 Hub4 Evaluation
E M Gales, E Eide, B Maison, M Gales, R Gopinath, S Chen, P Olsen, D Kanevsky, M Novak, L Mangu
in the 1999 hub4 evaluation, 2000

Penalized Maximum LikelihoodEstimators and the Baum Welch Algorithm for the Classifi cation of Acoustic Vectors in Speech Recognition
CA Micchelli, P Olsen
Journal of Computational and Applied Mathematics119, 301--331, 2000

Transcription of Broadcast News with a Time Constraint: IBM’s 10xRT HUB4 system
E Eide, B Maison, D Kanevsky, P Olsen, S Chen, L Mangu, M Gales, M Novak, R Gopinath
Proc, 2000

Transcription Of Broadcast News With A Time Constraint: IBM's 10xRT HUB4 System
D Kanevsky, P Olsen, S Chen, L Mangu, M Gales, M …
Sixth International Conference on Spoken Language Processing, 2000 - ISCA


IBM’s 10x Real-time Broadcast News Transcription System Used in the 1999 Hub4 Evaluation
E. Eide, B. Maison, M. Gales, R. Gopinath, S. Chen, P. Olsen, D. Kanevsky, M. Novak, L. Mangu
Proc. DARPA Speech Transcription Workshop, 2000

Maximum entropy and maximum likelihood criteria for feature selection from multivariate data
S. Basu, C.A. Micchelli, P. Olsen
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on, pp. 267--270, [New York: Acoustical Society of America]


1999

Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news
S.S. Chen, EM Eide, MJF Gales, R.A. Gopinath, D. Kanevsky, P. Olsen
Acoustics, Speech, and Signal Processing, 1999. ICASSP'99. Proceedings., 1999 IEEE International Conference on, pp. 37--40


Tail distribution modelling using the Richter and power exponential distributions
MJF Gales, PA Olsen
Sixth European Conference on Speech Communication and Technology, Citeseer, 1999

Maximum likelihood estimates for exponential type density families
S. Basu, C.A. Micchelli, P.A. Olsen
Acoustics, Speech, and Signal Processing, 1999. ICASSP'99. Proceedings., 1999 IEEE International Conference on, pp. 361--364

Recent improvements to IBM's speech recognition system forautomatic transcription of broadcast news
Gopinath, D Kanevsky, P Olsen, IBMTJWR Center, Y …
Acoustics, Speech, and Signal Processing, 1999. ICASSP'99. …, 1999 - ieeexplore.ieee.org


1998


IBM's LVCSR System for Transcription of Broadcast News used in the 1997 HUB4 English Evaluation
S. Chen, MJF Gales, PS Gopalakrishnan, RA Gopinath, H. Printz, D. Kanevsky, P. Olsen, L. Polymenakos
Proceedings of the Speech Recognition Workshop, 1998

Transcription of broadcast news-some recent improvements to IBM's LVCSR system
L. Polymenakos, P. Olsen, D. Kanvesky, RA Gopinath, PS Gopalakrishnan, S. Chen
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on, pp. 901--904


1997

Estimates on the solution of an elliptic equation related to Brownian motion with drift (II)
J G Conlon, P A Olsen
Revista matem{\'a}tica iberoamericana 13(3), 567--711, 1997


1996

Diffusion of directed polymers in a strong random environment
P Olsen, R Song
Journal of statistical physics 83(3), 727--738, Springer, 1996

A Brownian motion version of the directed polymer problem
J G Conlon, P A Olsen
Journal of statistical physics 84(3), 415--454, Springer, 1996


1993

Adaptation experiments on the spine database with the extended maximum likelihood linear transformation (EMLLT) model
R. Gopinath, V. Goel, K. Visweswariah, P. Olsen
Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on, pp. I--I


1992

note on irregular discrete wavelet transform IEEE Trans inform theory
P Olsen, K Seip
Information Theory, IEEE Transactions on 38(2), 861--863, IEEE, 1992


Year Unknown

SPECIAL ISSUE ON AUTOMATIC SPEECH RECOGNITION FOR MOBILE AND PORTABLE DEVICES
E. Chang, F. Seide, H. Meng, Z. Chen, Y. Shi, Y. Li, S. Deligne, S. Dharanipragada, R. Gopinath, B. Maison, others
ieeexplore.ieee.org, 0

AFFINE INVARIANT SPARSE MAXIMUM A POSTERIORI ADAPTATION
P.A. Olsen, J. Huang, S.J. Rennie, V. Goel
mirlab.org, 0