Publication List

Roni Rosenfeld, School of Computer Science, Carnegie Mellon University

Note: Many papers that appear in .pdf format below are also available, in the same directory, in the following formats: pdf.gz, ps, ps.gz.   Files that appear in a .doc.gz format below are also available, in the same directory, in a .doc format.

Speech and Language Technologies for Development:

• Jahanzeb Sherwani, Nosheen Ali, Sarwat Mirza, Anjum Fatma, Yousuf Memon, Mehtab Karim, Rahul Tongia, Roni Rosenfeld. HealthLine: Speech-based Access to Health Information by Low-literate Users. In Proc. IEEE/ACM Int'l Conference on Information and Communication Technologies and Development, Bangalore, India, December 2007.
• Jahanzeb Sherwani, Nosheen Ali, Rahul Tongia, Roni Rosenfeld, Yousuf Memon, Mehtab Karim, Gregory Pappas. HealthLine: Towards Speech-based Access to Health Information by Semi-literate Users. In Proc. Speech in Mobile and Pervasive Environments, Singapore, September 2007.
• Jahanzeb Sherwani, Rahul Tongia, Roni Rosenfeld, Yousuf Memon, Mehtab Karim, Gregory Pappas. Towards Speech Interfaces for Health Information Access by Semi-literate Users. In Proc. AI in ICT for Development,

Human-Machine Speech Communication:

• Jahanzeb Sherwani, Stefanie Tomko, and Roni Rosenfeld. Sublime: A Speech- and Language-based Information Management Environment. In Proc. IEEE Int.l Conference on Acoustics, Speech and Signal Processing, Toulouse, France, May 2006.
• Stefanie Tomko, Thomas K. Harris, Arthur Toth, James Sanders, Alexander Rudnicky, Roni Rosenfeld. Towards Efficient Human Machine Speech Communication: The Speech Graffiti Project. ACM Transactions on Speech and Language Processing, 2(1), February 2005..
• Stefanie Tomko and Roni Rosenfeld.  Shaping Spoken Input in User-Initiative Systems. Proc. ICSLP 2004.
• Thomas K. Harris and Roni Rosenfeld.  A Universal Speech Interface for Appliances.  Proc. ICSLP 2004.
• Stefanie Tomko and Roni Rosenfeld. Speech Graffiti vs. Natural Language: Assessing the User Experience.  Proc. HLT/NAACL, Boston, MA, 2004.
• Stefanie Tomko and Roni Rosenfeld. Speech Graffiti habitability: What do users really say? Proc. SIGDIAL, Boston, MA, 2004.
• Stanjeev Banerjee et. al. (group paper), Creating Multi-Modal, User-Centric Records of Meetings with the Carnegie Mellon Meeting Recorder Architecture, In Proc. ICASSP 2004.
• Brad A. Myers, Jeffrey Nichols, Jacob O. Wobbrock, Kevin Litwack, Michael Higgins, Joe Hughes, Thomas K. Harris, Roni Rosenfeld, Mathilde Pignol.  Handheld Devices for Control.  Human-Computer Interaction Consortium (HCIC 2003), Winter Park, CO, Feb 5-9, 2003.
• Jeffrey Nichols, Brad A. Myers, Michael Higgins, Joseph Hughes, Thomas K. Harris, Roni Rosenfeld, Kevin Litwack. Personal Universal Controllers: Controlling Complex Appliances With GUIs and Speech.  Extended Abstract CHI'2003: Human Factors in Computing Systems. (Demonstration Abstract). Fort Lauderdale, Florida, April 5-10, 2003. pp. 624-625.
• Arthur Toth, Thomas K. Harris, James Sanders, Stefanie Shriver, Roni Rosenfeld. Towards Every-Citizen's Speech Interface: An Application Generator for Speech Interfaces to Databases. Proc. 7th International Conference on Spoken Language Processing (ICSLP/Interspeech 2002).
• Jeffrey Nichols, Brad Myers, Thomas K. Harris, Roni Rosenfeld, Stefanie Shriver, Michael Higgins, Joseph Hughes. Requirements for Automatically Generating Multi-Modal Interfaces for Complex Appliances. Proc. IEEE Fourth International Conference on Multimodal Interfaces (ICMI'02), Pittsburgh, PA. October 14-16, 2002. pp. 377-382.
• Jeffrey Nichols, Brad Myers, Michael Higgins, Joseph Hughes, Thomas K. Harris, Roni Rosenfeld, Mathilde Pignol. Generating Remote Control Interfaces for Complex Appliances. 15th Annual Symposium on User Interface Software & Technology (UIST'02). 27-30 Oct. 2002, Paris, France. pp. 161-170.
• Stefanie Shriver and Roni Rosenfeld. Keyword Selection, and the Universal Speech Interface Project.  Proc. AVIOS, San Jose, CA, 2002.
• Stefanie Shriver and Roni Rosenfeld. Keywords for a Universal Speech Interface. Proc. ACM Conference on Human Factors in Computing Systems (CHI), Minneapolis, MN, 2002.
• Roni Rosenfeld, Dan Olsen and Alexander Rudnicky.  Universal Speech Interfaces. Interactions, VIII(6), 2001, pp. 34--44.   Earlier version published as A Universal Human-Machine Speech Interface. Technical Report CMU-CS-00-114, School of Computer Science,  Carnegie Mellon University, Pittsburgh, PA, March 2000.
• Stefanie Shriver, Arthur Toth, Xiaojin Zhu, Alex Rudnicky, Roni Rosenfeld. A Unified Design for Human-Machine Voice Interaction. In Proc. CHI 2001.
• Stefanie Shriver, Roni Rosenfeld, Xiaojin Zhu, Arthur Toth, Alex Rudnicky, Markus Flueckiger. Universalizing Speech: Notes from the USI Project. In Proc. Eurospeech 2001.
• Stefanie Shriver, Alan W Black and Roni Rosenfeld.  Audio Signals in Speech Interfaces.  In Proc. ICSLP 2000.
• Ronald Rosenfeld, Xiaojin Zhu, Stefanie Shriver, Arthur Toth, Kevin Lenzo, Alan W Black.  Towards a Universal Speech Interface.  In Proc. ICSLP 2000.

Computational Biology:

• Y. Lu, R. Rosenfeld, I. Simon, G.J. Nau and Z. Bar-Joseph, “A Probabilistic Generative Model for GO Enrichment Analysis”, RECOMB Satellite Conference on Systems Biology 2007. [conference website]
• Y. Lu, S. Mahony, P.V. Benos, R. Rosenfeld, I. Simon, L.L. Breeden and Z. Bar-Joseph, “Combined Analysis Reveals a Core Set of Cycling Genes,” Genome Biology 2007, 8:R146. [ pdf | http | supplements | supporting website ]
• Yong Lu, Roni Rosenfeld and Ziv Bar-Joseph. “Identifying Cycling Genes by Combining Sequence Homology and Expression Data”, BJ. Bioinformatics, 22(14):e314-322, 2006. Also presented in The Fourteenth International Conference on Intelligence Systems for Molecular Biology (ISMB 2006, Aug 7-10, Fortaleza, Brazil) [ bib | .pdf | http ].
• Henry C.M. Leung, Francis Y.L. Chin, S.M. Yiu, Roni Rosenfeld, W.W. Tsang, "Finding Motifs with Insufficient Number of Strong Binding Sites", Journal of Computational Biology 12(6), pp. 686–701, 2005.
• Rose Hoberman, Judith Klein-Seetharaman and Roni Rosenfeld, "Inferring Selection Pressure from Positional Residue Conservation", Appl. Bioinformatics. 2004; 3(2-3): 167-179 (pubmed, pdf). Also Proc. Biological Language Modeling Conference, November 2003 (Best Student Presentation award).
• Ziv Bar-Joseph, Shlomit Farkash, David K. Gifford, Itamar Simon and Roni Rosenfeld, "Deconvolving Cell-Cycle Expression Data with Complementary Information", ISMB'04, also to be published in J. BioInformatics.
• Francis Y.L. Chin, Henry C.M. Leung, S.M. Yiu, T.W. Lam, Roni Rosenfeld, W.W. Tsang, David K. Smith, Y.Jiang, "Finding Motifs for Insufficient Number of Sequences with Strong Binding to Transcription Factor", Proceedings of Annual International Conference on Research in Computational Molecular Biology (RECOMB), pages 125 - 132.
• Madhavi Ganapathiraju, Judith Klein-Seetharaman, Roni Rosenfeld, Jaime Carbonell and Raj Reddy,  "Comparative n-gram analysis of whole-genome sequences",  Proc. HLT'02: Human Language Technologies Conference, San Diego, March, 2002.
• Madhavi Ganapathiraju, Judith Klein-Seetharaman, Roni Rosenfeld, Jaime Carbonell and Raj Reddy, "Rare and frequent amino acid n-grams in whole-genome protein sequences", RECOMB'02: The Sixth Annual International Conference on Research in Computational Molecular Biology, Washington DC, USA, April, 2002.
• Madhavi Ganapathraju, Judith Klein-Seetharaman, Jaime Carbonell, Roni Rosenfeld and Raj Reddy,  "Comparative n-gram analysis of genome sequences", Proc. International Symposium On Crystallography And Bioinformatics in Structural Biology, Bangalore, India, November, 2001.
• Judith Klein-Seetharaman, Madhavi Ganapathiraju, Jaime Carbonell, Roni Rosenfeld and Raj Reddy, "Differences in usage of local combinations of amino acids in various genomes",  Proc. International Symposium On Crystallography And Bioinformatics in Structural Biology, Bangalore, India, November, 2001.

Statistical/Machine Learning Methods in Speech and Language Processing:

• Mark Johnson, Sanjeev Khudanpur, Mari Ostendorf and Roni Rosenfeld (eds.), Mathematical Foundations of Speech and Language Processing, the IMA volumes in Mathematics and Its Applications, 138, Springer, 2004.
• Xiaojin Zhu and Roni Rosenfeld, Improving Trigram Language Modeling with the World Wide Web. In Proc ICASSP 2001, longer version published as Technical Report CMU-CS-00-171.
• Roni Rosenfeld, Stanley F. Chen and Xiaojin Zhu.  Whole-Sentence Exponential Language Models: a Vehicle for Linguistic-Statistical Integration. Computers Speech and Language, 15(1), 2001. 
• Can Cai, Roni Rosenfeld and Larry Wasserman.  Exponential Language Models, Logistic Regression, and Semantic Coherence.  In Proc. NIST/DARPA Speech Transcription Workshop, May 2000.
• Chris Paciorek and Roni Rosenfeld.  Minimum Classification Error Training in Exponential Language Models.  In Proc. NIST/DARPA Speech Transcription Workshop, May 2000.
• Ronald Rosenfeld.  Two decades of Statistical Language Modeling: Where Do We Go From Here?  Proceedings of the IEEE,  88(8), 2000.
• Ronald Rosenfeld, Incorporating Linguistic Structure into Statistical Language Models, Philosophical Transactions of the Royal Society, Series A, 358 (1769), pp. 1311--1324, April 2000.
• Ronald Rosenfeld, Larry Wasserman, Can Cai, Xiaojin Zhu. Interactive Feature Induction and Logistic Regression for Whole Sentence Exponential Language Models. In Proc. IEEE workshop on Automatic Speech Recognition and Understanding, Keystone, Colorado, December 1999.
• Xiaojin Zhu, Stanley Chen and Ronald Rosenfeld. Linguistic Features for Whole Sentence Maximum Entropy Language Models. In Proc. Eurospeech '99, Hungary, September 1999.
• Kristie Seymore, Andrew McCallum and Ronald Rosenfeld. Learning Hidden Markov Model Structure for Information Extraction. AAAI'99 Workshop on Machine Learning for Information Extraction.
• Stanley Chen and Ronald Rosenfeld.  Efficient Sampling and Feature Selection in Whole Sentence Maximum Entropy Language Models.  In Proc. ICASSP '99, Phoenix, Arizona, March 1999.
• Adam Kalai, Stanley Chen, Avrim Blum and Ronald Rosenfeld. On-Line Algorithms for Combining Language Models. In Proc. ICASSP '99, Phoenix, Arizona, March 1999.
• Stanley Chen and Ronald Rosenfeld. A Survey of Smoothing Techniques for ME Models. IEEE Trans. Speech and Audio Processing,8(1), pp. 37--50. January 2000.  Also published as A Gaussian Prior for Smoothing Maximum Entropy Models, Technical Report CMU-CS-99-108, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, February 1999.
• Kristie Seymore, Stan Chen and Ronald Rosenfeld.  Nonlinear Interpolation of Topic Models for Language Model Adaptation.  In Proc. ICSLP98, Sydney, Australia.
• Andrew McCallum, Ronald Rosenfeld, Tom Mitchell and Andrew Ng.  Improving Text Classification by Shrinkage in a Hierarchy of Classes.  Intl. Conference on Machine Learning, ICML-98, July 1998.
• Stanley Chen, Kristie Seymore and Ronald Rosenfeld. Topic Adaptation for Language Modeling using Unnormalized Exponential Models.  In Proc. Int'l Conf. on Acoustics, Speech and Signal Processing, Seattle, Washington, May 1998.
• Stanley Chen, Douglas Beeferman and Ronald Rosenfeld. Evaluation Metrics for Language Models.  In Proc. DARPA Broadcast News Transcription and Understanding Workshop (BNTUW), Lansdowne, Virginia, February 1998.
• K. Seymore, S. Chen, S.J. Doh, M. Eskenazi, E. Gouvea, B. Raj, M. Ravishankar, R. Rosenfeld, M. Siegler, R. Stern and E. Thayer.  The 1997 CMU Sphinx-3 English Broadcast News Transcription System.  In Proc. DARPA Broadcast News Transcription and Understanding Workshop (BNTUW), Lansdowne, Virginia, February 1998.
• Ronald Rosenfeld. A Whole Sentence Maximum Entropy Language Model.  In Proc. IEEE workshop on Automatic Speech Recognition and Understanding, Santa Barbara, California, December 1997.
• Pierre Dupont and Ronald Rosenfeld. Lattice Based Language Models. Technical Report CMU-CS-97-173, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, September 1997.
• Kristie Seymore and Ronald Rosenfeld. Using Story Topics for Language Model Adaptation.  In Proc. Eurospeech '97, September 1997.  Longer version published as Large-Scale Topic Detection and Language Model Adaptation, Technical Report CMU-CS-97-152, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, June 1997.
• Philip Clarkson and Ronald Rosenfeld. Statistical Language Modeling using the CMU-Cambridge toolkit.  In Proc. Eurospeech '97, September 1997 (ELRA Best Student Paper Prize).
• Andreas Stolcke, Ciprian Chelba, David Engle, Victor Jimenez, Lidia Mangu, Harry Printz, Eric Ristad, Ronald Rosenfeld, Dekai Wu. Structure and Performance of a dependency language model.  In Proc. Eurospeech'97, September 1997.
• Kristie Seymore, Stanley Chen, Maxine Eskenazi and Ronald Rosenfeld. Language and Pronunciation Modeling in the CMU 1996 Hub 4 Evaluation.  In Proc. ARPA Spoken Langauge Technology Workshop, Chantilly, VA, February 1997.
• P. Placeway, S. Chen, M. Eskenazi, U. Jain, V. Parikh, B. Raj, M. Ravishankar, R. Rosenfeld, K. Seymore, M. Siegler, R. Stern and E. Thayer.  The 1996 Hub-4 Sphinx-3 System.  In Proc. ARPA Spoken Langauge Technology Workshop,Chantilly, VA, February 1997.
• Ronald Rosenfeld. A Maximum Entropy Approach to Adaptive Statistical Language Modeling. Computer, Speech and Language 10, 187--228, 1996 (2001 award for “Most Influential Paper in CSL in the Last 5 Years").  Longer version published as Adaptive Statistical Language Modeling: A Maximum Entropy Approach, Ph.D. thesis, Computer Science Department, Carnegie Mellon University,TR CMU-CS-94-138, April 1994.
• Kristie Seymore and Ronald Rosenfeld.  Scalable Backoff Language Models.  In Proc. ICSLP'96, Philadelphia, October 1996.  Longer version published as Scalable Trigram Backoff Language Models, Technical Report CMU-CS-96-139, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, May 1996.
• Lin Chase, Kristie Seymore and Roni Rosenfeld.  Language Modeling for Large Vocabulary Conversational Speech Recognition. Workshop on Large Vocabulary Conversational Speech Recognition, Maritime Institue of Technology, Linthicum Heights, Maryland, April 29--May 1, 1996.
• Ronald Rosenfeld, Rajeev Agarwal, Bill Byrne, Rukmini Iyer, MarkLiberman, Liz Shriberg, Jack Unverferth, Dimitra Vergyri, EnriqueVidal.  Error Analysis and Language Modeling for Conversational Speech: TeamReport.  In Proceedings of the 1995 Language Modeling Workshop, Johns Hopkins University, July--August 1995.
• Ronald Rosenfeld. Optimizing Lexical and Ngram Coverage Via Judicious Use of Linguistic Data.  In Proc. Eurospeech'95, Madrid, Spain, September 1995.
• Ronald Rosenfeld. An Impact Matrix for the 1994 CSR Hub Evaluation.  In Proc. ARPA Spoken Language Technology Workshop, Austin, TX, January 1995.
• Ronald Rosenfeld. The CMU Statistical Language Modeling Toolkit, and its use in the 1994 ARPA CSR Evaluation.  In Proc. ARPA Spoken Language Technology Workshop, Austin, TX, January 1995.
• L. Chase, R. Rosenfeld, A. Hauptmann, M. Ravishankar, E. Thayer, P.Placeway, R. Weide, C. Lu.  Improvements in Language, Lexical, and Phonetic Modeling in Sphinx-II.  In Proc. ARPA Spoken Langauge Technology Workshop, Austin, TX, January 1995.
• Lin Chase, Ron Rosenfeld, and Wayne Ward.  Error-Responsive Modifications to Speech Recognizers: Negative N-grams.  In Proc. International Conference on Spoken Language Processing, Yokohama, Japan, September 1994.
• M. Hwang, R. Rosenfeld, E. Thayer, R. Mosur, L. Chase, R. Weide, X. Huang, and F. Alleva.  Improving Speech-Recognition Performance via Phone-Dependent VQ Codebooks and Adaptive Language Models in SPHINX-II.  In Proc. Int'l Conf. on Acoustics, Speech and Signal Processing, Australia, April 1994.
• Ronald Rosenfeld. A Hybrid Approach to Adaptive Statistical Language Modeling.  In Proc. ARPA Human Language Technology Workshop, Plainsboro, NJ, March 1994.
• R. Rosenfeld, E. Thayer, R. Mosur, L. Chase, R. Weide, M. Hwang,X. Huang and F. Alleva. Improved Acoustic and Adaptive Language Models for Continuous Speech Recognition.  In Proc. ARPA Spoken Language Systems Workshop, March 1994.
• Francis Kubala, Jerome Bellegarda, Jordan Cohen, Dave Pallett, Doug Paul, Mike Phillips, Raja Rajasekaran, Fred Richardson, Mike Riley, Roni Rosenfeld, Bob Roth, MitchWeintraub. The Hub and Spoke Paradigm for CSR Evaluation.  In Proc. ARPA Human Language Technology Workshop, Plainsboro, NJ, March 1994.
• Chase, L., Mosur, R., and Rosenfeld, R. Language Model Adaptation in the CSR Evaluation.  ARPA Spoken Language Systems Workshop, Plainsboro, NJ, March 1994.
• Ronald Rosenfeld. Modeling Long-Distance Linguistic Phenomena Within the Maximum Entropy Framework.  Invited speaker at IEEE Automatic Speech Recognition workshop, Snowbird, UT, December 1993.
• Raymond Lau, Ronald Rosenfeld, and Salim Roukos. Trigger-based Language Models Using Maximum Likelihood Estimation of Exponential Distributions.  In Proc. Int'l Conf. on Acoustics, Speech and Signal Processing, Minneapolis, MN, April 1993.
• Raymond Lau, Ronald Rosenfeld, and Salim Roukos. Adaptive Language Modeling Using the Maximum Entropy Principle.  In Proc. ARPA Human Language Technology Workshop, March 1993.
• Raymond Lau, Ronald Rosenfeld, and Salim Roukos. Building Scalable N-gram Language Models Using Maximum Likelihood Maximum Entropy N-gram models. U.S. Patent 5,467,425, February 1993.
• Xuedong Huang, Fil Alleva, Mei-Yuh Hwang, and Ronald Rosenfeld. An Overview of the SPHINX-II Speech Recognition System.  In Proc. ARPA Human Language Technology Workshop, March 1993.
• Xuedong Huang, Fil Alleva, Mei-Yuh Hwang, Ronald Rosenfeld, and Rich Stern. The SPHINX-II system used in the DARPA 1992 evaluation.  DARPA Spoken Language Technology Workshop, Boston, MA, January 1993.
• Ronald Rosenfeld. Adaptive Statistical Language Modeling: A Maximum Entropy Approach.  Ph.D. thesis proposal, Carnegie Mellon University, October 1992.
• Ronald Rosenfeld, Xuedong Huang and Merrick Furst. Exploiting Correlations Among Competing Models with Application to Large Vocabulary Speech Recognition.  In Proc. Int'l Conf. on Acoustics, Speech and Signal Processing, San Francisco, CA, March 1992.
• X.D. Huang, F. Alleva, H.W. Hon, M.Y. Hwang, K.F. Lee, and R. Rosenfeld. The SPHINX-II Speech Recognition System: An Overview. Computer, Speech and Language, 2, pages 137--148, 1993.  Also published as Technical Report CMU-CS-92-112, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, February, 1992.
• F. Alleva, H. Hon, X. Huang, M. Hwang, R. Rosenfeld, and R. Weide. Applying SPHINX-II to the DARPA Wall Street Journal CSR Task.  In Proc. DARPA Speech and Language Workshop, Morgan Kaufmann Publishers,San Mateo, CA, February 1992.
• Ronald Rosenfeld and Xuedong Huang. Improvements in Stochastic Language Modeling.  In Proc. DARPA Speech and Language Workshop, Morgan Kaufmann Publishers, San Mateo, CA, February 1992.
• Ronald Rosenfeld, Xuedong Huang and Merrick Furst. Exploiting Correlations Among Models with Application to Large Vocabulary Speech Recognition. Technical Report CMU-CS-91-148, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, May, 1991.
• Barak Pearlmutter and Ronald Rosenfeld. Chaitin-Kolmogorov Complexity and Generalization in Neural Networks.  In D. Touretzky, J. Moody and R. Lippmann (eds.), Advances in Neural Information Processing Systems 3. San Mateo, CA: Morgan Kaufmann, 1991.
• Ronald Rosenfeld and David S. Touretzky. Coarse-Coded Symbol Memories and Their Properties.  Journal of Complex Systems, 2(4), pp. 463-484, August 1988.
• Ronald Rosenfeld and David S. Touretzky. A Survey of Coarse-Coded Symbol Memories.  In Proceedings of the 1988 Connectionist Models Summer School, Carnegie Mellon, June 17-26, 1988. Morgan Kaufmann, 1989.
• Ronald Rosenfeld and David S. Touretzky. Four Capacity Models of Coarse-Coded Symbol Memories. Technical Report CMU-CS-87-182, Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, December, 1987.
• Ronald Rosenfeld and David S. Touretzky. Scaling Properties of Coarse-Coded Symbol Memories.  In Dana Z. Anderson (Ed.), Neural Information Processing Systems 1, pp.652--661, AIP, New York, 1988.
• Ronald Rosenfeld, David S. Touretzky and the Boltzmann Research Group.  Connectionist Models as Neural Abstractions: commentary on ``Brains Make Chaos to Make Sense of the World'' by C.A. Skarda and W.J. Freeman.  In Behavioral and Brain Sciences, 10(2), June 1987, pp.181-183.