Michael Riley has a B.S., M.S., and Ph.D. from MIT, all in computer science. He began his career at Bell Labs and AT&T Labs where he, together with Mehryar Mohri and Fernando Pereira, introduced and developed the theory and use of weighted finite-state transducers (WFSTs) in speech and language. He is currently a senior staff research scientist at Google, Inc. His interests include speech and natural language processing, machine learning, and information retrieval. He is a principal author of the OpenFst library and the AT&T FSM Library (TM). He manages a group with expertise that includes natural language parsing, document and sentiment analysis, automata and speech recognition algorithms, and machine learning.
“Mobile Music Modeling, Analysis and Recognition”, Pavel Golik, Boulos Harb, Ananya Misra, Michael Riley, Alex Rudnick, Eugene Weinstein, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012.
[abstract] [pdf] [search]
“A Filter-based Algorithm for Efficient Composition of Finite-State Transducers”, Cyril Allauzen, Michael Riley, Johan Schalkwyk, International Journal of Foundations of Computer Science (2011).
[pdf] [search]
“Bayesian Language Model Interpolation for Mobile Speech Input”, Cyril Allauzen, Michael Riley, Interspeech 2011, pp. 1429-1432.
[abstract] [pdf] [search]
“Hierarchical Phrase-Based Translation Representations”, Gonzalo Iglesias, Cyril Allauzen, William Byrne, Adrià de Gispert, Michael Riley, Proceedings of EMNLP 2011.
[pdf] [search]
“Language Modeling for Automatic Speech Recognition Meets the Web: Google Search by Voice”, Ciprian Chelba, Johan Schalkwyk, Boulos Harb, Carolina Parada, Cyril Allauzen, Michael Riley, Peng Xu, Thorsten Brants, Vida Ha, Will Neveitt, 2011.
[abstract] [seminar.csee.ogi.edu] [pdf] [search]
“Direct Construction of Compact Context-Dependency Transducers From Data”, David Rybach, Michael Riley, Interspeech 2010.
[abstract] [pdf] [search]
“Expected Sequence Similarity Maximization”, Cyril Allauzen, Shankar Kumar, Wolfgang Macherey, Mehryar Mohri, Michael Riley, NAACL HLT, 2010.
[aclweb.org] [pdf] [search]
“Filters for Efficient Composition of Weighted Finite-State Transducers”, Cyril Allauzen, Michael Riley, Johan Schalkwyk, CIAA, 2010, pp. 28-38.
[pdf] [search]
“A Generalized Composition Algorithm for Weighted Finite-State Transducers”, Cyril Allauzen, Michael Riley, Johan Schalkwyk, Interspeech 2009.
[abstract] [pdf] [search]
“OpenFst: An Open-Source, Weighted Finite-State Transducer Library and its Applications to Speech and Language”, Michael Riley, Cyril Allauzen, Martin Jansche, Proceedings of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT) 2009 conference, Tutorials.
[abstract] [aclweb.org] [pdf] [search]
“Web Derived Pronunciations for Spoken Term Detection”, Doğan Can, Erica Cooper, Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Bhuvana Ramabhadran, Michael Riley, Murat Saraçlar, Abhinav Sethy, Morgan Ulinski, Christopher White, 32nd Annual International ACM SIGIR Conference, 2009, pp. 83-90.
[abstract] [pdf] [search]
“Web-derived Pronunciations”, Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Michael Riley, Morgan Ulinski, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2009, pp. 4289-4292.
[abstract] [doi] [pdf] [search]
“On the Computation of the Relative Entropy of Probabilistic Automata”, Corinna Cortes, Mehryar Mohri, Ashish Rastogi, Michael Riley, International Journal of Foundations of Computer Science, vol. 19 (2008), pp. 219-242.
[cs.nyu.edu] [search]
“Sample Selection Bias Correction Theory”, Corinna Cortes, Mehryar Mohri, Michael Riley, Afshin Rostamizadeh, Proceedings of The 19th International Conference on Algorithmic Learning Theory (ALT 2008).
[cs.nyu.edu] [pdf] [search]
“Speech Recognition with Weighted Finite-State Transducers”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Handbook on Speech Processing and Speech Communication, Part E: Speech recognition, 2008.
[cs.nyu.edu] [search]
“OpenFst: a General and Efficient Weighted Finite-State Transducer Library”, Cyril Allauzen, Michael Riley, Johan Schalkwyk, Wojciech Skut, Mehryar Mohri, Proceedings of the 12th International Conference on Implementation and Application of Automata (CIAA 2007).
[search]
“On the Computation of the Relative Entropy of Probabilistic Automata”, Corinna Cortes, Mehryar Mohri, Ashish Rastogi, Michael Riley, International Journal of Foundations of Computer Science, vol. to appear (2007).
[cs.nyu.edu] [search]
“Speech Recognition with Weighted Finite-State Transducers”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Handbook on Speech Processing and Speech Communication, Part E: Speech recognition, 2007.
[cs.nyu.edu] [search]
“Efficient Computation of the Relative Entropy of Probabilistic Automata”, Corinna Cortes, Mehryar Mohri, Ashish Rastogi, Michael Riley, Proceedings of the 7th Latin American Symposium (LATIN 2006).
[cs.nyu.edu] [search]
“Weighted Automata in Text and Speech Processing”, Mehryar Mohri, Fernando Pereira, Michael Riley, arXiv, vol. abs/cs/0503077 (2005).
[arxiv.org] [search]
“A Generalized Construction of Integrated Speech Recognition Transducers”, Cyril Allauzen, Mehryar Mohri, Brian Roark, Michael Riley, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2004).
[cs.nyu.edu] [search]
“Statistical Modeling for Unit Selection in Speech Synthesis”, Cyril Allauzen, Mehryar Mohri, Michael Riley, 42nd Meeting of the Association for Computational Linguistics (ACL 2004), Proceedings of the Conference.
[cs.nyu.edu] [search]
“Statistical Modeling for Unit Selection in Speech Synthesis”, Cyril Allauzen, Mehryar Mohri, Michael Riley, $42$nd Meeting of the Association for Computational Linguistics (ACL 2004), Proceedings of the Conference.
[cs.nyu.edu] [search]
“Voice Signatures”, Izhak Shafran, Michael Riley, Mehryar Mohri, Proceedings of The 8th IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2003).
[cs.nyu.edu] [search]
“An Efficient Algorithm for the N-Best-Strings Problem”, Mehryar Mohri, Michael Riley, Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02).
[cs.nyu.edu] [search]
“A Comparison of Two LVR Search Optimization Techniques”, Stephan Kanthak, Hermann Ney, Michael Riley, Mehryar Mohri, Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02).
[cs.nyu.edu] [search]
“An Efficient Algorithm for the $N$-Best-Strings Problem”, Mehryar Mohri, Michael Riley, Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02).
[cs.nyu.edu] [search]
“Weighted Finite-State Transducers in Speech Recognition (Tutorial)”, Mehryar Mohri, Michael Riley, Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02).
[search]
“Weighted Finite-State Transducers in Speech Recognition”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Computer Speech and Language, vol. 16 (2002), pp. 69-88.
[cs.nyu.edu] [search]
“A Weight Pushing Algorithm for Large Vocabulary Speech Recognition”, Mehryar Mohri, Michael Riley, Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech '01), 2001.
[cs.nyu.edu] [search]
“The Design Principles of a Weighted Finite-State Transducer Library”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Theoretical Computer Science, vol. 231 (2000), pp. 17-32.
[cs.nyu.edu] [search]
“Weighted Finite-State Transducers in Speech Recognition”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Proceedings of the ISCA Tutorial and Research Workshop, Automatic Speech Recognition: Challenges for the new Millenium (ASR2000).
[cs.nyu.edu] [search]
“Efficient General Lattice Generation and Rescoring”, Andrej Ljolje, Fernando Pereira, Michael Riley, EUROSPEECH 99, 1999, pp. 1251-1254.
[telecom.tuc.gr] [search]
“Integrated Context-Dependent Networks in Very Large Vocabulary Speech Recognition”, Mehryar Mohri, Michael Riley, Proceedings of the 6th European Conference on Speech Communication and Technology (Eurospeech '99), 1999.
[cs.nyu.edu] [search]
“Network Optimizations for Large Vocabulary Speech Recognition”, Mehryar Mohri, Michael Riley, Speech Communication, vol. 28 (1999), pp. 1-12.
[cs.nyu.edu] [search]
“Rapid Unit Selection from a Large Speech Corpus for Concatenative Speech Synthesis”, Mark Beutnagel, Mehryar Mohri, Michael Riley, Proceedings of the 6th European Conference on Speech Communication and Technology (Eurospeech '99), 1999.
[cs.nyu.edu] [search]
“A Rational Design for a Weighted Finite-State Transducer Library”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Proceedings of the Second International Workshop on Implementing Automata (WIA '97), 1998, pp. 144-158.
[search]
“Full Expansion of Context-Dependent Networks in Large Vocabulary Speech Recognition”, Mehryar Mohri, Michael Riley, Don Hindle, Andrej Ljolje, Fernando C. N. Pereira, Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP '98), 1998.
[cs.nyu.edu] [search]
“A Rational Design for a Weighted Finite-State Transducer Library”, Mehryar Mohri, Fernando Pereira, Michael Riley, WIA'97: Proceedings of the Workshop on Implementing Automata, 1997.
[research.att.com] [search]
“Speech Recognition by Composition of Weighted Finite Automata”, Fernando Pereira, Michael Riley, Finite-State Language Processing, 1997, pp. 431-453.
[cis.upenn.edu] [search]
“Transducer Composition for Context-Dependent Network Expansion”, Michael Riley, Fernando Pereira, Mehryar Mohri, EuroSpeech'97, 1997, pp. 1427-1430.
[search]
“A Rational Design for a Weighted Finite-State Transducer Library”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Proceedings of the Workshop on Implementing Automata (WIA '97), London, Ontario, Canada, 1997.
[search]
“Transducer Composition for Context-Dependent Network Expansion”, Michael Riley, Fernando C. N. Pereira, Mehryar Mohri, Proceedings of the 5th European Conference on Speech Communication and Technology (Eurospeech '97), 1997.
[search]
“Weighted Determinization and Minimization for Large Vocabulary Speech Recognition”, Mehryar Mohri, Michael Riley, Proceedings of the 5th European Conference on Speech Communication and Technology (Eurospeech '97), 1997.
[search]
“Algorithms for Speech Recognition and Language Processing”, Mehryar Mohri, Michael Riley, Richard Sproat, CoRR, vol. cmp-lg/9608018 (1996).
[arxiv.org] [search]
“Compilation of Weighted Finite-State Transducers from Decision Trees”, Richard Sproat, Michael Riley, ACL, 1996, pp. 215-222.
[search]
“Compilation of Weighted Finite-State Transducers from Decision Trees”, Richard Sproat, Michael Riley, CoRR, vol. cmp-lg/9606018 (1996).
[arxiv.org] [search]
“Speech Recognition by Composition of Weighted Finite Automata”, Fernando C. N. Pereira, Michael Riley, 1996.
[arxiv.org] [search]
“Finite-State Transducers in Language and Speech Processing”, Mehryar Mohri, Michael Riley, Richard Sproat, Tutorial at the 16th International Conference on Computational Linguistics (COLING-96), 1996.
[search]
Rational Power Series in Text and Speech Processing, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, 1996.
[search]
“Weighted Automata in Text and Speech Processing”, Mehryar Mohri, Fernando C. N. Pereira, Michael Riley, Proceedings of the 12th biennial European Conference on Artificial Intelligence (ECAI-96), Workshop on Extended finite state models of language, 1996.
[cs.nyu.edu] [search]
“The AT&T 60,000 Word Speech-to-Text System”, Michael Riley, Andrej Ljolje, Don Hindle, Fernando Pereira, Eurospeech'95: ESCA 4th European Conference on Speech Communication and Technology, 1995, pp. 207-210.
[search]
“Weighted Rational Transductions and their Application to Human Language Processing”, Fernando Pereira, Michael Riley, Richard W. Sproat, Human Language Technology Workshop, 1994, pp. 262-267.
[search]
“A spoken language translator for restricted-domain context-free languages”, David B. Roe, Pedro J. Moreno, Richard W. Sproat, Fernando Pereira, Michael Riley, Alejandro Macarrón, Speech Communication, vol. 11 (1992), pp. 311-319.
[search]
“Efficient Grammar Processing for a Spoken Language Translation System”, David B. Roe, Pedro J. Moreno, Richard W. Sproat, Fernando Pereira, Michael Riley, Alejandro Macarrón, Proceedings of ICASSP, 1992, pp. 213-216.
[search]
“Toward a Spoken Language Translator for Restricted-Domain Context-Free Languages”, David B. Roe, Fernando Pereira, Richard W. Sproat, Michael Riley, Pedro J. Moreno, Alejandro Macarrón, EUROSPEECH 91 - 2nd European Conference on Speech Communication and Technology, 1991, pp. 1063-1066.
[search]