Ciprian Chelba is a Research Scientist with Google. Previously he worked as a Researcher in the Speech Technology Group at Microsoft Research.
His research interests are in statistical modeling of natural language and speech. Recent projects include: Google Audio Indexing: indexing, ranking and snippeting of speech content; Language Modeling for Google Search by Voice.
An Audio Indexing System for Election Video Material, Christopher Alberti, Michiel Bacchiani, Ari Bezman, Ciprian Chelba, Anastassia Drofa, Hank Liao, Pedro Moreno, Ted Power, Arnaud Sahuguet, Maria Shugrina, Olivier Siohan, Proceedings of ICASSP, 2009, pp. 4873-4876.
Back-Off Language Model Compression, Boulos Harb, Ciprian Chelba, Jeffrey Dean, Sanjay Ghemawat, Proceedings of Interspeech 2009, pp. 325-355.
Acoustic Sensitive Language Model Perplexity for Automatic Speech Recognition, Ciprian Chelba, Proceedings of Machine Learning Workshop, 2006.
Adaptation of maximum entropy capitalizer: Little data can help a lot, Ciprian Chelba, Alex Acero, Computer Speech and Language, vol. 20 (2006), pp. 382-399.
Integration of Metadata in Spoken Document Search Using Position Specific Posterior Lattices, Jorge Silva, Ciprian Chelba, Alex Acero, Proceedings of the IEEE International Workshop on Spoken Language Technology, 2006, to appear.
Pruning Analysis of the Position Specific Posterior Lattices for Spoken Document Search, Jorge Silva Sanchez, Ciprian Chelba, Alex Acero, Proceedings of ICASSP'06, 2006, to appear.
Soft Indexing of Speech Content for Search in Spoken Documents, Ciprian Chelba, Jorge Silva, Alex Acero, Computer Speech and Language (2006), pp. 458-478.
Towards Spoken-Document Retrieval for the Internet: Lattice Indexing For Large-Scale Web-Search Architectures, Zheng-Yu Zhou, Peng Yu, Ciprian Chelba, Frank Seide, Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, 2006, pp. 415-422.
Indexing Uncertainty for Spoken Document Search, Ciprian Chelba, Alex Acero, Proceedings of Eurospeech, 2005, pp. 61-64.
Position Specific Posterior Lattices for Indexing Speech, Ciprian Chelba, Alex Acero, Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05), 2005, pp. 443-450.
SPEECH OGLE: Indexing Uncertainty for Spoken Document Search, Ciprian Chelba, Alex Acero, Proceedings of the ACL Interactive Poster and Demonstration Sessions, 2005, pp. 41-44.
Adaptation of Maximum Entropy Capitalizer: Little Data Can Help a Lot, Ciprian Chelba, Alex Acero, Proceedings of EMNLP, 2004, pp. 285-292.
Conditional Maximum Likelihood Estimation of Naive Bayes Probability Models, Ciprian Chelba, Alex Acero, 2004.
Conditional Maximum Likelihood Estimation of Naive Bayes Probability Models Using Rational Function Growth Transform, Ciprian Chelba, Alex Acero, Proceedings of Machine Learning Workshop, 2004.
Parsing Conversational Speech Using Enhanced Segmentation, Jeremy G. Kahn, Mari Ostendorf, Ciprian Chelba, HLT-NAACL 2004: Short Papers, pp. 125-128.
Discriminative Training of N-gram Classifiers for Speech and Text Routing, Ciprian Chelba, Alex Acero, Proceedings of Eurospeech 2003, pp. 1-4.
Speech Utterance Classification, C. Chelba, M. Mahajan, A. Acero, Proceedings of ICASSP, 2003, pp. 280-283.
A Study on Richer Syntactic Dependencies for Structured Language Modeling, Peng Xu, Ciprian Chelba, Frederick Jelinek, ACL, 2002, pp. 191-198.
Growth Transform for Conditional Maximum Likelihood Estimation of Log-Linear Models, Milind Mahajan, Ciprian Chelba, 2002.
Mutual Information Phone Clustering for Decision Tree Induction, C. Chelba, R. Morton, Proc. Int. Conf. on Spoken Language Processing, 2002.
Information Extraction Using the Structured Language Model, Ciprian Chelba, Milind Mahajan, Proceedings of EMNLP, 2001, pp. 74-81.
Portability of Syntactic Structure for Language Modeling, Ciprian Chelba, Proceedings of the IEEE International Conference on Audio, Speech and Signal Processing Conference, 2001.
Richer Syntactic Dependencies for Structured Language Modeling, C. Chelba, P. Xu, Proc. of the IEEE Workshop on Automatic Speech Recognition and Understanding, 2001.
Richer Syntactic Dependencies for Structured Language Modeling, Ciprian Chelba, Peng Xu, Proceedings of Automatic Speech Recognition and Understanding Workshop, 2001.
Exploiting Syntactic Structure for Natural Language Modeling, Ciprian Chelba, 2000.
Structured Language Modeling, Ciprian Chelba, Frederick Jelinek, Computer Speech and Language, vol. 14 (2000), pp. 283-332.
Putting Language into Language Modeling, Frederick Jelinek, Ciprian Chelba, Proceedings of Eurospeech'99, 1999.
Recognition performance of a structured language model, C. Chelba, F. Jelinek, Proceedings of Eurospeech, 1999.
Structured Language Modeling for Speech Recognition, Ciprian Chelba, Frederick Jelinek, Proceedings of NLDB, 1999.
Exploiting Syntactic Structure for Language Modeling, Ciprian Chelba, Frederick Jelinek, Proceedings of COLING-ACL, 1998, pp. 225-231.
Refinement of a Structured Language Model, Ciprian Chelba, Frederick Jelinek, Proceedings of ICAPR, 1998.
A Structured Language Model, Ciprian Chelba, Proceedings of ACL-EACL, 1997, 498-500,student section.
Structure and Performance of a Dependency Language Model, C. Chelba, D. Engle, F. Jelinek, V. Jimenez, S. Khudanpur, L. Mangu, H. Printz, E. S. Ristad, R. Rosenfeld, A. Stolcke, D. Wu, Proceedings of Eurospeech, 1997, pp. 2775-2778.