The Center for Spoken Language Understanding
Oregon Health & Science University
Speech and language processing: algorithms for extracting
information from spoken language, including large vocabulary speech
recognition, acoustic modeling, spoken term detection, and prosody
Machine learning: learning finite state machines for speech
recognition, and developing frameworks for recognizing speaker
characteristics (e.g., emotion and dialect) from limited amounts of
Example applications: Tools for assessing cognitive function and
social engagement in older adults, screening patients for Parkinson's
disease, modeling social behavior in macaques, recognizing speech in
noisy and everyday settings, and exploiting prosody to improve
downstream processing (e.g., parsing and disfluency detection)
CS 552/652: Automatic Speech Recognition
CS 548/648: Probabilitistic Graphical Models
CS 506/606: Special Topics: Large Vocabulary Recognition
CS 506/606: Special Topics: Problem Solving with Large Clusters
CS 559/659: Machine Learning
CS 547/647: Statistical Pattern Recognition
CS 506/606: Probabilistic Graphical Models
Current Students & Postdocs Maider Lehr, Graduate Student
Meysam Asgari, Graduate Student
Alireza Bayesteh, Graduate Student
Golnar Sheikhshabbafghi, Graduate Student
Shiran Dudy, Graduate Student
Ranjani Ramakrishnan, Graduate Student
Guillaume Thiebault, Post-doctoral Fellow
Past Students & Postdocs
Anthony Stark, Post-doctoral Fellow (now at Microsoft)
Christian Monson, Post-doctoral Fellow (now at Amazon)
Open PositionsPostdoctoral Fellow: We are seeking
outstanding graduates to fill a postdoctoral fellowship. Graduates of
Computer Science or Electrical Engineering with background in machine
learning or applications of it in speech and language processing or
computer vision are encouraged to apply. For more information, see
Research Computing System Administration
Speech and Language
Medicine and Health
The articles presented below are meant for timely
dissemination of scholarly and technical work and may not be reposted
without the explicit permission of the copyright holder. Copyright and
all rights therein are retained by authors or by other copyright
Inferring social nature of conversations from words: Experiments on a
corpus of everyday telephone conversations, Anthony Stark,
Izhak Shafran, and Jeffrey Kaye, Computer Speech and Language,
Volume 28, Issue 1, Pages 224-239, January 2014.
- Parsimonious Multivariate Copula
Model for Density Estimation, Alireza Bayestehtashk and Izhak
Shafran, Proc. IEEE ICASSP, 2013.
- Discriminative Joint Modeling of
Lexical Variation and Acoustic Confusion for Automated Narrative
Retelling Assessment, Maider Lehr, Izhak Shafran, Emily
Prud'hommeaux and Brian Roark, Proc. NAACL, 2013.
- Robust and Accurate Features for
Detecting and Diagnosing Autism Spectrum Disorders, Meysam
Asgari, Alireza Bayestehtashk, and Izhak Shafran, Won the Interspeech Challenge on Diagnosing Autism
Spectral Disorders, Proc. Interspeech, 2013.
- Improving the Accuracy and the
Robustness of Harmonic Model for Pitch Estimation, Meysam
Asgari and Izhak Shafran, Proc. Interspeech, 2013.
- Adaptive H-Extrema For Automatic Immunogold Particle
Detection, Guillaume Thibault, Kristiina Iljin, Christopher
Arthur, Izhak Shafran, and Joe Gray, Proc. Congress on Pattern
Recognition, Havana, Cuba, 2013.
- Visual Hull Reconstruction for Automated Primate Behavior
Observation, Nastaran Ghadar, Xikang Zhang, Kang Li, Deniz
Erdogmus, Guillaume Thibault, Alireza Bayesteh, Izhak Shafran Kris
Coleman, and Kathleen A. Grant, Machine Learning for Signal
- Robust Detection of Voiced Segments in
Samples of Everyday Conversations Using Unsupervised HMMs,
Meysam Asgari, Izhak Shafran and Alireza Bayestehtashk, Proc. IEEE
Spoken Language Technology (SLT), 2012.
- Hello, Who is Calling?: Can Words
Reveal the Social Nature of Conversations?, Anthony Stark, Izhak
Shafran and Jeffrey Kaye, Proc. Conference of the North American
Chapter of the Association for Computational Linguistics and Human
Language Technology (NAACL/HLT), 2012.
- Fully Automated Neuropsychological
Assessment for Detecting Mild Cognitive Impairment, Maider
Lehr, Emily Prud'hommeaux, Izhak Shafran and Brian Roark,
Proc. Interspeech, 2012.
- Deriving conversation-based features
from unlabeled speech for discriminative language modeling,
D.Karakos, B.Roark, I.Shafran, K.Sagae, M.Lehr, E.Prud'hommeaux, P.Xu,
N.Glenn, S.Khudanpur, M.Saraclar, D.Bikel, M.Dredze, C.Callison-Burch,
Y.Cao, K.Hall, E.Hasler, P.Koehn, A.Lopez, M.Post, and D.Riley,
Proc. Interspeech, 2012.
- Interspeech Pathology Challenge: Investigations into Speaker
and Sentence Specific Effects, Anthony Stark, Alireza
Bayestehtashk, Meysam Asgari and Izhak Shafran, Proc. Interspeech,
- Hallucinated N-best Lists for
Discriminative Language Modeling, K.Sagae, M.Lehr,
E.Prud'hommeaux, P.Xu, N.Glenn, D.Karakos, S.Khudanpur, B.Roark,
M.Saraclar, I.Shafran, D.Bikel, C.Callison-Burch, Y.Cao, K.Hall,
E.Hasler, P.Koehn, A.Lopez, M.Post, and D.Riley, ICASSP, 2012.
- Continuous Space Discriminative
Language Modeling, P.Xu, S.Khudanpur, M.Lehr,
E.Prud'hommeaux, N.Glenn, D.Karakos, B.Roark, K.Sagae, M.Saraclar,
I.Shafran, D.Bikel, C.Callison-Burch, Y.Cao, K.Hall, E.Hasler,
P.Koehn, A.Lopez, M.Post, and D.Riley, ICASSP, 2012.
- Semi-supervised Discriminative
Language Modeling for Turkish ASR, A.Celeba, H.Sak,
E.Dikici, M.S M.Saraclar, M.Lehr, E.Prud'hommeaux, P.Xu, N.Glenn,
D.Karakos, S.Khudanpur, B.Roark, K.Sagae, I.Shafran, D.Bikel,
C.Callison-Burch, Y.Cao, K.Hall, E.Hasler, P.Koehn, A.Lopez, M.Post,
and D.Riley, ICASSP, 2012.
- Supervised and Unsupervised Feature
Selection for Inferring Social Nature of Telephone Conversations
from Their Content, Anthony Stark, Izhak Shafran and Jeffrey
Kaye, Proc. Automatic Speech Recognition and Understanding, 2011.
- Efficient Determinization of Tagged
Word Lattices using Categorial and Lexicographic Semirings,
Izhak Shafran, Richard Sproat, Mahsa Yarmohammadi and Brian Roark,
Proc. Automatic Speech Recognition and Understanding, 2011.
- Lexicographic Semirings for Exact
Automata Encoding of Sequence Models, Brian Roark, Richard
Sproat and Izhak Shafran, Best Short Paper
Award, ACL 2011.
- Learning a Discriminative Weighted
Finite-State Transducer for Speech Recognition, Maider Lehr
and Izhak Shafran, IEEE Transaction on Audio, Speech and Language
Processing, vol. 19, no 5, pp. 1360--1367, July 2011.
- Discriminatively Estimated Discrete,
Parametric and Smoothed-Discrete Duration Models for Speech
Recognition, M. Lehr and I. Shafran, Proc. IEEE ICASSP,
pp. 5340-5343, 2011.
- Discriminatively Estimated Joint
Acoustic, Duration and Language Model for Speech
Recognition, Maider Lehr and Izhak Shafran, Proc. ICASSP,
2nd Best Student Paper Award (ASR), 2010.
- Predicting Severity of Parkinson's
Disease from Speech, Meysam Asgari and Izhak Shafran,
Proc. IEEE EMBS, 2010.
- Syntactic and Sub-lexical Features for
Turkish Discriminative Language Models, Ebru Arisoy, Murat
Saraclar, Brian Roark, and Izhak Shafran, Proc. ICASSP, 2010.
- Extracting Cues from Speech For
Predicting Severity of Parkinson's Disease, Meysam Asgari
and Izhak Shafran, Proc. IEEE MLSP, 2010.
- Classifying clear and conversational speech based on acoustic
features, Akiko Amano-Kusumoto, John-Paul Hosom, and Izhak
Shafran, Proc. Interspeech, 2009.
- Discriminative N-gram Language Modeling
for Turkish, Ebru Arisoy, Brian Roark, Izhak Shafran and
Murat Saraclar, Proc. Interspeech, pages 825-28, Brisbane, Australia,
Sept. 22-26, 2008.
- Multiple Heteroscedastic Linear
Discriminant Analysis, Izhak Shafran and Haolang Zhou,
CLSP Research Note 54, draft.
- Exploiting Prosody for PCFGs with
Latent Annotations, Markus Dreyer and Izhak Shafran,
Proc. Interspeech, Aug. 27-31, Antwerp, Belgium, 2007.
- The SRI/OGI 2006 Spoken Term Detection
System, Dimitra Vergyri, Izhak Shafran, Andreas Stolcke,
Ramana R. Gadde, Murat Akbacak, Brian Roark, and Wen Wang,
Proc. Interspeech 2007, Aug. 27-31, Antwerp, Belgium, 2007.
- Multi-Stream Fusion for Speaker Classification (chapter),
Izhak Shafran, Speaker Classification (Lecture notes in Computer
Science and Artificial Intelligence), Springer,
Heidelberg-Berlin-New York, vol. 4343, 2007.
- Overview of the CLEF- 2006
cross-language speech retrieval track, Douglas W. Oard,
Jianqiang Wang, Gareth J. F. Jones, Ryan W. White, Pavel Pecina,
Dagobert Soergel, Xiaoli Huang, and Izhak Shafran, In Working
Notes of the CLEF-2006 Evaluation, Alicante, Spain, 12 pages,
- Corrective Models for Speech
Recognition of Inflected Languages, Izhak Shafran, and Keith
Hall, Proc. of the Conference on Empirical Methods in Natural
Language Processing (EMNLP), pages 390-8, Sydney, Australia,
July 22-23, 2006.
- PCFGs with Syntactic and Prosodic
Indicators of Speech Repairs , John Hale, Izhak Shafran,
Lisa Yung, Bonnie Dorr, Mary Harper, Anna Krasnyanskaya, Mathew
Lease, Yang Liu, Brian Roark, Mathew Snover, and Robin Stewart,
Proc. of the joint conference of the International Committee on
Computational Linguistics and the Association for Computational
Linguistics (COLING/ACL), pages 161-8, Sydney, Australia, July
- Discriminative classifiers for
language recognition, Christopher White, Izhak Shafran, and
Jean-luc Gauvain, Proc. of IEEE Int'l Conference on Acoustic
Signal and Speech Processing (ICASSP), vol 1, pages 213-6,
Toulouse, France, May 14-19, 2006.
- Reranking for sentence boundary
detection in conversational speech, Brian Roark, Yang Liu,
Mary Harper, Robin Stewart, Mathew Lease, Mathew Snover, Izhak
Shafran, Bonnie Dorr, John Hale, Anna Krasnyanskaya, and Lisa Yung,
Proc. of IEEE Int'l Conference on Acoustic Signal and Speech
Processing (ICASSP), vol 1, pages 545-8, Toulouse, France, May
- SParseval: Evaluation Metrics for
Parsing Speech, Brian Roark, Mary Harper, Eugene Charniak,
Bonnie Dorr, Mark Johnson, Jeremy G. Kahn, Yang Liu, Mari Ostendorf,
John Hale, Anna Krasnyanskaya, Matthew Lease, Izhak Shafran, Matthew
Snover, Robin Stewart, and Lisa Yung, Proc. Language Resources
and Evaluation (LREC), Genoa, Italy, 2006.
- Acoustic and Language Modeling for MALACH
Czech ASR System, Izhak Shafran, CLSP Research Note
No. 52, The Johns Hopkins University, 2006.
- Accent Detection and Speech Recognition
for Shanghai-Accented Mandarin, Yanli Zheng, Richard Sproat,
Liang Gu, Izhak Shafran, Haolang Zhou, Yi Su, Dan Jurafsky, Rebecca
Starr and Su-Youn Yoon,9th European Conference on Speech
Communication and Technology (Eurospeech), Lisboa, Portugal,
- A comparison of classifiers for
detecting emotion from speech, Izhak Shafran and Mehryar
Mohri, Proc. of IEEE Int'l Conference on Acoustic Signal and
Speech Processing (ICASSP), Philadelphia, PA, Mar 19-23, vol. 1,
pp. 341-344, 2005.
- Task-Specific Minimum Bayes-Risk
Decoding using Learned Edit Distance, Izhak Shafran and
William Byrne, Proc. of INTERSPEECH2004-ICSLP, vol. 3,
pp. 1945-48, Jeju Islands, Korea, Oct. 4-8, 2004.
- Voice Signatures, Izhak
Shafran, Michael Riley and Mehryar Mohri, Proc. of IEEE Automatic
Speech Recognition and Understanding Workshop (ASRU), US Virgin
Islands, Nov 30-Dec 4, pp. 31-36, 2003.
- Robust Speech Detection and
Segmentation for Real-Time ASR Applications, Izhak Shafran
and Richard Rose, Proc. of IEEE Int'l Conference on Acoustic
Signal and Speech Processing (ICASSP), vol. 1, pp. 432-45, Hong
- Prosody Models for Conversational
Speech Recognition, Mari Ostendorf, Izhak Shafran and
Rebecca Bates, Proc. of the 2nd Plenary Meeting and Symposium on
Prosody and Speech Processing, Invited Paper,
pp. 147-154, 2003.
- Acoustic model clustering based on
syllable structure, Izhak Shafran and Mari Ostendorf,
Computer Speech and Language, vol. 17(4), pg. 311-328, 2003.
- Prosody and phonetic variability:
Lessons learned from acoustic model clustering, Izhak
Shafran, Mari Ostendorf and Richard Wright, Proc. ISCA Tutorial
and Research Workshop on Prosody in Speech Recognition and
Understanding, pg. 127--131, 2001.
- A prosodically labeled database of
spontaneous speech, Mari Ostendorf, Izhak Shafran, Stefanie
Shattuck-Hufnagel, Leslie Carmichael and William Byrne,
Proc. ISCA Tutorial and Research Workshop on Prosody in Speech
Recognition and Understanding, pg. 119--121, 2001.
- Use of higher level linguistic
structure in acoustic modeling for speech recognition, Izhak
Shafran and Mari Ostendorf, Proc. IEEE Int'l Conference on
Acoustic Signal and Speech Processing (ICASSP), vol. 2,
pg. 1021-1024, Istanbul, Turkey, Jun 5-9, 2000.
- Clustering wide-contexts and HMM topologies for
Spontaneous Speech Recognition, Izhak Shafran,
Ph.D. Thesis, University of Washington, Seattle, 2001.
- Inferring functional connectivity
in MRI using Bayesian network structure learning with a modified PC
algorithm, Swathi P Iyer, Izhak Shafran, David Grayson, Joel
T Nigg, Kathleen M Gates, and Damien Fair, NeuroImage, 2013.
- Towards Automatic Surgical Skill
Evaluation: Detection and Segmentation of Robotic-Sugrical
Motions, Henry Lin, Izhak Shafran, David Yuh, and Gregory
D. Hagery, Journal of Computer Aided Surgery, Invited Paper, vol. 11, No.5, pp. 20-30, 2006.
- Vision-Assisted Automatic Detection and Segmentation of
Robot-Assisted Surgical Motions, Henry Lin, Izhak Shafran, David
D. Yuh, and Gregory D. Hager, Medicine Meets Virtual Reality
14, Long Beach, CA, 2006.
- Automatic Detection and Segmentation
of Robot-Assisted Surgical Motions, Henry Lin, Izhak
Shafran, Todd E. Murphy, Allison M. Okamura, David D. Yuh, and
Gregory D. Hager, 8th International Conference on Medical Image
Computing and Computer Assisted Intervention (MICCAI), MICCAI Student Paper Award, vol. I,
pp. 802-810, Palm Springs, CA, 2005.
- Naturalistic and Objective Measures of Social Engagement via
Automated Spoken Language Processing Izhak Shafran, Anthony
Stark, Nicole Larimer, Maider Lehr, Nora Mattek, Jon Yeagers,
Katherine Wild, and Jeffrey Kaye, Abstract at the GSA Annual
- Parsing and Spoken Structural Event
Detection, Mary Harper, Bonnie J. Dorr, John Hale, Brian
Roark, Izhak Shafran, Matthew Lease, Yang Liu, Matthew Snover, Lisa
Yung, Anna Krasnyanskaya, and Robin Stewart, Final Report of 2005
Johns Hopkins Summer Workshop, 2005.
- The JHU 2004 Chinese-English
and Arabic-English MT Evaluation Systems, Shankar Kumar,
Yonggang Deng, Charles Schafer, Woosung Kim, Paola Virga, Nizar
Habash, David Smith, Filip Jurcicek, Bill Byrne, Sanjeev Khudanpur,
Izhak Shafran, and David Yarowsky, NIST Machine Translation 2004
Evaluation. June 22, 2004.
- AT&T 1xRT CTS STT System,
Enrico Bocchieri, Andrej Ljolje, Michael Riley, Brian Roark, Murat
Saraclar and Izhak Shafran, DARPA Rich Transcription
Workshop, unpublished presentation, Boston, Spring 2003.
- Coherent de-dispersion system for GMRT, Izhak Shafran,
Yashwant Gupta and C. R. Subramanya, Proc. 6th Asia Pacific Meet
on Astronomy, Int'l Astronomical Union, 1993.
- Feeds for GMRT, G. Sankarasubramanian, M. R. Shankaraman,
Izhak Shafran, et. al., Proc. 6th Asia Pacific Meet on
Astronomy, Int'l Astronomical Union, 1993.
- Signal Processing for Analyzing Pulsars, Izhak Shafran,
M.Tech. Thesis, Electrical Engineering, Indian Institute of
Technology, Bombay (Mumbai), 1996.
- Checkout recent
discoveries using Giant Meterwave Radio Telescope (GMRT)!
Some useful links:
3181 SW Sam Jackson Park Rd, GH40
Portland, OR 97239-3098
zakshafran at gmail nospam com
A MacBook Pro with the serial number W80411Z6ATP was stolen from me on Dec 24th 2010 in Barecelona, Spain. If anyone finds it, please contact me.