Signal and Image Processing
University of Washington
Seattle, WA 98195
|Phone: (206) 221-5748
Stanford University PhD 1985
Stanford University MS 1981
Stanford University BS 1980
Mari Ostendorf joined the Speech Signal Processing Group at BBN Laboratories in 1985, where she worked on low-rate coding and acoustic modeling for continuous speech recognition. Two years later, she moved to Boston University in the Department of Electrical and Computer Engineering, where she her research expanded to include language modeling, prosody modeling, and speech synthesis. She joined the University of Washington in 1999, where she is broadly interested in spoken language technology. She teaches courses in statistical language processing and undergraduate signal processing, and has recently introduced a class on the Digital World of Multimedia, introducing new undergraduates to signal processing and communications. Her current research efforts are centered on rich speech transcription, particularly for purposes of automatic language processing on speech, with more fundamental interests in learning methods for language technology. She has published over 150 papers on various problems in speech and language processing. Dr. Ostendorf has served on the Speech Processing and the DSP Education Committees of the IEEE Signal Processing Society and numerous workshop committees.
Endowed Professor of System Design Methodologies
IEEE Fellow 2005
1998 ATR Interpreting Telecommunications Laboratories Paper Award
1999 IEEE Signal Processing Society Paper Award
Statistical modeling for signal interpretation and generation, particularly speech and language processing. Current research efforts are in acoustic and language modeling for rich transcription of spoken language, the use of prosody at the interface between speech and language, learning with sparse data resources, and language technology for bilingual education.
Signal, Speech, and Language Interpretation Lab: http://ssli.ee.washington.edu/
O. Cetin, M. Ostendorf and G. Bernard, "Multi-rate Hidden Markov Models for Monitoring of Machining Tool Wear," IEEE Trans. Signal Processing, to appear 2007.
R. Bates, M. Ostendorf and R. Wright, "Symbolic phonetic features for modeling of pronunciation variation," Speech Communication, to appear 2007.
I. Bulyko, M. Ostendorf, M. Siu, T. Ng, A. Stolcke and O. Cetin, "Web resources for language modeling in conversational speech recognition," ACM Trans. on Speech and Language Processing, to appear 2007.
with A. Stolcke et al., "Recent innovations in speech-to-text transcription at SRI-ICSI-UW," IEEE Trans. Audio, Speech and Language Processing, Vol 14, No. 5, 2006.
with Y. Liu et al., "Enriching speech recognition with automatic detection of sentence boundaries and disfluencies," IEEE Trans. Audio, Speech and Language Processing, Vol. 14, No. 5, 2006.
M. Siu, T. Ng, and M. Ostendorf, "A quantitative assessment of the importance of tone in Mandarin speech recognition," Signal Processing Letters, Vol. 12, No. 12, pp. 867-870, 2005.
I. Bulyko, K. Kirchhoff, M. Ostendorf and J. Goldberg, "Error-correction detection and response generation in a spoken dialogue system," Speech Communication, Vol. 45. No. 3, 2005, pp. 271-288.
D. Palmer and M. Ostendorf, "Improving Out-of-Vocabulary Name Resolution," Computer Speech and Language, vol. 19, no. 1, pp. 107-128, 2005.
M. Ostendorf and I. Bulyko, "The Use of Speech Recognition Technology in Speech Synthesis," in Text-to-Speech Synthesis: New Paradigms and Advances, ed. S. Narayanan and A. Alwan, Prentice Hall, 2004.
S. Schwarm, I. Bulyko and M. Ostendorf, "Adaptive language modeling with varied sources to cover new vocabulary items," IEEE Trans. Speech and Audio Processing, vol. 12, no. 3, pp. 334-342, 2004.
Selected Recent Conference Papers
B. Hoffmeister, D. Hillard, S. Hahn, R. Schulter, M. Ostendorf and H. Ney, "Cross-site and intra-site ASR system combination: Comparisons on lattice and 1-best methods," Proc. ICASSP, 2007.
T. Shinozaki and M. Ostendorf, "Cross-validation EM training fro robust parameter estimation," Proc. ICASSP, 2007
X. Lei and M. Ostendorf, "Word-level tone modeling for Mandarin speech recognition," Proc. ICASSP, 2007.
A. Mandal, M. Ostendorf and A. Stolcke, "Speaker clustered regression-class trees for MLLR adaptation," Proc. Interspeech, 2006, pp. 1133-1136.
S. Hahn, R. Ladner and M. Ostendorf, "Agreement/disagreement classification: exploiting unlabeled data using contrast classifiers," Proc. HLT-NAACL, pp. 53-56, 2006.
D. Hillard, Z. Huang, H. Ji, R. Grishman, D. Hakkani-Tur, M. Harper, M. Ostendorf and W. Wang, "Impact of automatic comma prediction on POS and name tagging of speech," Proc. IEEE/ACL Workshop on Spoken Language Technology, 2006.
W. McNeill, J. Kahn, D. Hillard and M. Ostendorf, "Phrase structure and segmentation for improving speech recognition," Proc. IEEE/ACL Workshop on Spoken Language Technology, 2006.
C. Boulis and M. Ostendorf, "Using symbolic prominence to help design feature subsets for topic classification and clustering of natural human-human conversations," Proc. Interspeech Conference, pp. 425-428, 2005.
J. G. Kahn, M. Lease, E. Charniak, M. Johnson and M. Ostendorf, "Effective use of prosody in parsing conversational speech," Proc. EMNLP-HLT, pp. 233-240, 2005.
S. Schwarm and M. Ostendorf, "Reading Level Assessment Using Support Vector Machines and Statistical Language Models," Proc. ACL, 2005.
C. Boulis and M. Ostendorf, "Combining multiple clustering systems," Proc. European Conference on Principles of Knowledge Discovery in Databases, pp. 63-74, 2004.
M. Ostendorf and H. Singer, "Maximum likelihood state splitting for continuous speech recognition"
GALE: Rich Transcription for Machine Translation, DARPA, 9/05-11/07
A Collaborative Program for EE Systems Education, NSF, 9/05-9/07
ITR: Translation Technology for Language Modeling, NSF, 9/03-9/07
Recent Graduate Students
Xin Lei, EE Ph.D. 2006, "Modeling lexical tones for Mandarin large vocabulary continuous speech recognition"
William McNeill, Linguistics M.A. 2006, "Segmentation and Feature Selection for Conversational Speech Syntactic Language Models"
Jeremy G. Kahn, Linguistics M.A. 2005, "Moving beyond the lexical layer in parsing conversational speech"
Constantinos Boulis, EE Ph.D. 2005, University of Washington, "Topic Learning in Text and Conversational Speech"
Ozgur Cetin, EE Ph.D. 2004, University of Washington, "Multi-rate modeling, model inference and estimation for statistical classifiers"
Rebecca Bates, EE Ph.D. 2004, University of Washington, "Dynamic pronunciation modeling in spontaneous speech recognition"
Current Graduate Students
Arindam Mandal, EE Ph.D. expected 2007, "Pronunciation modeling in spontaneous speech recognition"
Sarah Petersen, CSE Ph.D. expected 2007, "Language technology for reading-level assessment in bilingual education"
Dustin Hillard, EE Ph.D. expected 2007, "Detecting sentence structure in speech for machine translation"
Scott Otterson, EE Ph.D. candidate, "Tracking speakers in meeting recordings"
Sangyun Hahn, CSE Ph.D. candidate, "Semi-supervised learning techniques for annotating activities in meetings"
Jeremy G. Kahn, Linguistics Ph.D. candidate, "Use of parsing in machine translation"
Alex Marin, EE Ph.D. candidate, "Query-driven topic language model adaptation"
Amy Dashiell, EE M.S. candidate, "Detecting emotion and intent for dialog systems"
IEEE Transactions on Audio, Speech and Language Processing, Editor 2006-2008
Computer, Speech and Language, Editor 1998-2003