SEAS Department Website

Dan Ellis has been with the Columbia University Department of Electrical Engineering since fall 2000, before which he was a senior research scientist at the International Computer Science Institute in Berkeley, California. Professor Ellis is a member of the IEEE, the Acoustical Society of America, and the International Speech Communications Association. He has served on the organizing committee of several meetings, including the IEEE workshop on Applications of Signal Processing to Acoustics and Audio, and several recent workshops on Computational Auditory Scene Analysis. He is also the administrator of the AUDITORY email discussion list.

• Ph.D., Electrical Engineering and Computer Science, MIT (1996)
• M.S., Electrical Engineering and Computer Science, MIT (1992)
• B.A. (hons.), Engineering (ranked top), Cambridge University, U.K. (1987)

• Computational models of human sound processing and organization
• Automatic speech recognition in real-world environments
• Indexing, browsing, and visualization tools for audio archives

• Postdoctoral Researcher / Senior Research Scientist, International Computer Science Institute, Berkeley, Calif. (1996–2000)
• Research Assistant, M.I.T., Media Lab (1989–96)
• Intern, Interval Research Corporation, Palo Alto, Calif. (Summer 1994)
• Member of technical staff, AWARE, Inc., Cambridge, Mass. (1991–93)

Cooke, M.P. & Ellis, D.P.W. "The auditory organization of speech in listeners and machines," Speech Communication (accepted for publication).

Ellis, D.P.W. & Bilmes, J.A. "Using mutual information to design feature combinations," Proc. Int. Conf. Spoken Lang. Proc., Beijing, December 2000 (to appear).

Barker, J., Cooke, M. & Ellis, D. "Decoding speech in the presence of other sound sources," Proc. Int. Conf. Spoken Lang. Proc., Beijing, December 2000 (to appear).

Ferreiros, J. & Ellis, D. "Using acoustic condition clustering to improve acoustic change detection on Broadcast News," Proc. Int. Conf. Spoken Lang. Proc., Beijing, December 2000 (to appear).

Hermansky, H., Ellis, D. & Sharma, S. "Tandem connectionist feature stream extraction for conventional HMM systems," Proc. IEEE Int. Conf. on Acous., Speech and Sig. Proc., Istanbul, III-1635-1638, June 2000.

Sharma, S., Ellis, D., Kajarekar, S., Jain, P. & Hermansky, H. (2000). "Feature extraction using non-linear transformation for robust speech recognition on the Aurora database," Proc. IEEE Int. Conf. on Acous., Speech and Sig. Proc., Istanbul, II-1117-1120, June 2000.

Ellis, D.P.W. "Improved recognition by combining different features and different systems," Proc. Mtg. American Voice Input Output Soc., San Jose, May 2000.

Ellis, D.P.W. "Using knowledge to organize sound: The prediction-driven approach to compu-tational auditory scene analysis, and its application to speech/nonspeech mixtures," Speech Communication 27(3-4), 281-298, 1999.

Genoud, D., Ellis, D. & Morgan, N. "Combined speech and speaker recognition with speaker-adapted connectionist models," Proc. IEEE Automatic Speech Recognition & Under-standing Workshop, Keystone CO, December 1999.

Abberley, D., Renals, S., Ellis, D. & Robinson, T. "The THISL SDR system at TREC-8," Proc. Text Retrireview Conference TREC-8, Washington, November 1999.

Ellis, D.P.W. & Williams, G. "Speech/music discrimination based on posterior probability features," Proc. Eurospeech-99, Budapest, September 1999.

Janin, A., Ellis, D. & Morgan, N. "Multistream: Ready for prime-time?" Proc. Eurospeech-99, Budapest, September 1999.

Ellis, D. & Morgan, N. "Size matters: An empirical study of neural network training for large vocabulary continuous speech recognition," Proc. IEEE Int. Conf. on Acous., Speech & Sig. Proc., Phoenix, April 1999.

Morgan, N., Ellis, D., Fosler-Lussier, E., Janin, A. & Kingsbury, B. "Reducing errors by increasing the error rate: MLP acoustic modeling for Broadcast News transcription," DARPA Broadcast News Transcription and Understanding Workshop, Herndon VA, February 1999.

Cook, G., Christie, J., Ellis, D., Fosler-Lussier, E., Gotoh, Y., Kingsbury, B., Morgan, N., Renals, S., Robinson, A. & Williams, G. "An overview of the SPRACH system for the tran-scription of Broadcast News," DARPA Broadcast News Transcription and Understanding Workshop, Herndon VA, February 1999.

Ellis, D.P.W. & Rosenthal, D.F. "Mid-Level representations for Computational Auditory Scene Analysis," in: D.F. Rosenthal & H.G. Okuno (eds.) Computational Auditory Scene Analysis (Lawrence Erlbaum, Mahwah), pp. 257-272, 1998.

Ellis, D.P.W. "Computational Auditory Scene Analysis exploiting speech recognizer knowl-edge," Proc. IEEE Workshop on Apps. of Sig. Proc. to Acous. and Audio, Mohonk, October 1997.

Ellis, D.P.W. "The Weft: a representation for periodic sounds," Proc. IEEE Int. Conf. on Acous., Speech & Sig. Proc., Munich, April 1997.

Greenberg, S., Hollenback, J. & Ellis, D.P.W. "Insights into spoken language gleaned from phonetic transcriptions of the Switchboard corpus," Proc. Int. Conf. on Spoken Lang. Proc., Philadelphia, October 1996.

Ellis, D.P.W. "Prediction-driven computational auditory scene analysis for dense sound mix-tures," Proc. ESCA Workshop on the Auditory Basis of Speech Perception, Keele, July 1996.

Ellis, D.P.W. "Underconstrained stochastic representations for top-down computational audi-tory scene analysis," Proc. IEEE Workshop on Apps. of Sig. Proc. to Acous. and Audio, Mohonk, October 1995.

Ellis, D.P.W. "A computer implementation of psychoacoustic grouping rules," Proc. 12th Int. Conf. on Pattern Recog., Jerusalem, October 1994.