Esther Levin

 

Selected Publications.

·        Kate Acomb, Jonathan Bloom, Krishna Dayanidhi, Phillip Hunter, Peter Krogh, Esther Levin, Roberto Pieraccini, “Technical Support Dialog Systems: Issues, Problems, and Solutions “, in Proc. HLT-NAACL 06,  Rochester, NY,  April 22-27, 2007.

  • E. Levin, M. Sharifi and J. Ball, ‘Evaluation of Utility of LSA for Word Sense Discrimination’ in Proc. HLT-NAACL 06, June 4-8, NY, NY.
  • E. Levin & A. Levin, ‘Dialog Design for User Adaptation’, in Proc. ICASSP 2006,  May 14-19, 2006, Toulouse, France.
  • E. Levin & A.M. Mane, ‘Voice User Interface Design for Automated Directory Assistance‘, in Proc. INTERSPEECH 2005, September 4-8, 2005, Lisbon, Portugal
  • E. Levin & A. Levin, ‘Spoken Dialog System for Real-Time Data Capture‘, in Proc. INTERSPEECH 2005, September 4-8, 2005, Lisbon, Portugal.
  • Amir M. Mane, Esther Levin, (in press) ‘Designing the Voice User Interface for Automated Directory Assistance‘, To appear in In D. Gardner-Bonneau & H. E. Blanchard (Eds.) Human factors and voice interactive systems Second Edition. Norwell, MA: Kluwer.
  • Levin, E., Narayanan, S., Pieraccini, R., Biatov, K., Bocchieri, E., Di Fabbrizio, G., Eckert, W., Lee, S., Pokrovsky, A., Rahim, M., Ruscitti, P., Walker, L., ‘The AT&T-DARPA Communicator Mixed-Initiative Spoken Dialog System, ‘Proc. ICSLP 2000, Beijing, China, Oct. 2000
  • Levin, E., Pieraccini, R., Eckert, W., ‘A Stochastic Model of Human-Machine Interaction for Learning Dialog Strategies, ‘, IEEE Trans. on Speech and Audio Processing, Vol. 8, No. 1, pp. 11-23, January 2000
  • Levin, E., Pieraccini, R., Eckert, W., Di Fabbrizio, G., Narayanan, S., ‘Spoken Language Dialogue: from Theory to Practice,‘ Proc. of ASRU99– IEEE Workshop, Keystone, Colorado, Dec. 1999.
  • Levin, E., Pieraccini, R. and Eckert, W., ‘Using Markov decision process for learning dialogue strategies,‘ Proc. ICASSP 98, Seattle, WA, May, 1998.
  • Levin, E. and Pieraccini, R., ‘A stochastic model of computer-human interaction for learning dialogue strategies,’ Proc. of EUROSPEECH 97, Rhodes, Greece, Sept. 1997.
  • Pieraccini, R., Levin, E. and Eckert, W., ‘AMICA: the AT&T Mixed Initiative Conversational Architecture,‘ Proc. of EUROSPEECH 97, Rhodes, Greece, Sept. 1997.
  • Eckert, W., Levin, E. and Pieraccini, R., ``User modeling for spoken dialogue system,'' ASRU '97, 1997.
  • Levin, E., Pieraccini, R. and Eckert, W., ``A stochastic model of computer-human interaction for learning dialogue strategies,'' ASRU '97, 1997.
  • Levin, E. and Pieraccini, R., ``CHRONUS, the next generation,'' Proc. 1995 ARPA Spoken Language Sstems Tech. Workshop, Austin, Texas, Jan. 1995.
  • Levin, E. and Pieraccini, R., ``Concept-based spontaneous speech understanding system,'' Proc. EUROSPEECH '95, Madrid, Spain, 1995.
  • Pieraccini, R. and Levin, E., ``A spontaneous-speech understanding system for database query applications,'' ESCA Workshop Spoken Dialogue Systems - Theories and Applications, Denmark, 1995. .
  • Vapnik, V., E. Levin and LeCun, Y., ``Measuring the VC-dimension of a Learning Machine,'' Neural Computation, vol. 6, no. 5, 1994, pp. 851-876.
  • Pieraccini, R., Levin, E. and Vidal, E., ``Learning how to understand language,'' Proc. EUROSPEECH '93, Berlin, Germany, Sept. 1993, pp. 1407-1414.
  • Vidal, E., Pieraccini, R. and Levin, E., ``Learning associations between grammars: A new approach to natural language understanding,'' Proc. EUROSPEECH '93, Berlin, Germany, Sept. 1993, pp. 1187-1190.
  • Agazzi, O. E., Kuo, S., Levin, E. and Pieraccini, R., ``Connected and degraded text recognition using planal hidden Markov models,'' Proc. IEEE Int. Conf. Acoust., Speech, & Sig. Processing, Minneapolis, April 1993.
  • Levin, E., ``Hidden control neural architecture modeling of nonlinear time varying systems and its application,'' IEEE Trans. Neural Networks, vol. 4, no. 1, Jan. 1993.
  • Levin, E., Pieraccini, R. and Bocchieri, E., ``Time-warping network: A hybrid framework for speech recognition,'' Int. J. Pattern Recognition & Artificial Intelligence, 1993.
  • Solla, S. A. and Levin, E., ``Learning in neural networks: The validity of the annealed approximation,'' Physical Review, Aug. 1992.
  • Levin, E. and Pieraccini, R., ``Dynamic planar warping for optical character recognition,'' Proc. ICASSP '92, vol. 3, San Francisco, CA, March, 1992, pp. 149-152.
  • Pieraccini, R. and Levin, E., ``Stochastic representation of semantic structure for speech understanding,'' Speech Communication, vol. 11, 1992, pp. 238-288.
  • Pieraccini, R. and Levin, E., ``Stochastic representation of semantic structure for speech understanding,'' Proc. EUROSPEECH '91, Genova, Italy, Sept. 1991.
  • Pieraccini, R., Levin, E. and Lee, C-H., ``Stochastic representation of conceptual structure in the ATIS task,'' Proc. Fourth Joint DARPA Speech and Natural Lang. Workshop, Pacific Grove, CA, Feb. 1991.
  • Levin, E., Tishby, N. Z. and Solla, S. A., ``A statistical approach to learning and generalization,'' Proc. IEEE, Oct. 1990.
  • Levin, E., Tishby, N. and Solla, S. A., ``Statistical learning & generalization in layered networks,'' Spec. Issue on Neural Networks Proc. IEEE, Oct. 1990.
  • Levin, E., ``A Recurrent neural network: limitation and training,'' Neural Networks Journal, vol. 3, 1990, pp. 641-650.
  • Levin, E., ``Continuous speech recognition with hidden control neural networks,'' Proc. Speech Tech, 1990, Invited paper.
  • Levin, E., ``Modeling time varying systems using HCNN with application to speech recognition,'' Proc. of NIPS, Denver, 1990.
  • Levin, E., Levin, E., ``Word recognition using hidden control neural architecture,'' Proc. ICASSP '90, 1990.
  • Levin, E., Tishby, N. and Solla, S. A., ``A statistical approach to learning & generalization in layered neural networks,'' Proc. Workshop Comp. Learning Theory, Rivest, R. and Haussler, D. (Ed.), Santa-Cruz, 1989.
  • Tishby, N., Levin, E. and Solla, S. A., ``Consistent inference of probabilities in layered networks: predictions & generalization,'' Proc. Int. Joint Conf. Neural Networks, vol. II, 1989.