Papers by Dan Ellis


NB: This page has been superceded by the version at Columbia, please go there for more recent publications.

This is an almost comprehensive list of my published papers and other substantial research writings.


A.L. Berenzweig and D.P.W. Ellis (2001). Locating Singing Voice Segments within Music Signals
Submitted to IEEE Workshop on Apps. of Sig. Proc. to Acous. and Audio, Mohonk NY, October 2001. (4pp)

D.P.W. Ellis and M.J. Reyes Gomez (2001). Investigations into Tandem Acoustic Modeling for the Aurora Task
Submitted to Eurospeech-01 Special Event on Noise Robust Recognition, Denmark, September 2001. (4pp)

T. Pfau and D.P.W. Ellis (2001). Hidden Markov Model Based Speech Actitivity Detection for the ICSI Meeting Project
Submitted to Eurospeech-01, Denmark, September 2001. (4pp)

N. Morgan, D. Baron, J. Edwards, D. Ellis, D. Gelbart, A. Janin, T. Pfau, E. Shriberg and A. Stolcke (2001). The Meeting Project at ICSI
Human Language Technologies Conference, San Diego, March 2001. (7pp)

D.P.W. Ellis, R. Singh and S. Sivadas (2001). Tandem acoustic modeling in large-vocabulary recognition
Proc. ICASSP-2001, Salt Lake City, May 2001. (4pp)
See also the poster I presented at the conference.

D.P.W. Ellis and J.A. Bilmes (2000). Using mutual information to design feature combinations
Proc. ICSLP-2000, Beijing, October 2000. (4pp)

J. Barker, M. Cooke and D. Ellis (2000). Decoding speech in the presence of other sound sources
Proc. ICSLP-2000, Beijing, October 2000. (4pp)

J. Ferreiros Lopez and D.P.W. Ellis (2000). Using acoustic condition clustering to improve acoustic change detection on Broadcast News
Proc. ICSLP-2000, Beijing, October 2000. (4pp)

D.P.W. Ellis (2000). Improved recognition by combining different features and different systems
Proc. AVIOS-2000, San Jose, May 2000. (7pp)

D.P.W. Ellis (2000). Stream combination before and/or after the acoustic model
Rejected from ICASSP-2000, now an ICSI tech. report. (4pp)

H. Hermansky, D. Ellis and S. Sharma (2000). Tandem connectionist feature stream extraction for conventional HMM systems
Proc. ICASSP-2000, Istanbul, III-1635-1638. (4pp)
See also the poster I presented at the conference.

S. Sharma, D. Ellis, S. Kajarekar, P. Jain and H. Hermansky (2000). Feature extraction using non-linear transformation for robust speech recognition on the Aurora database
Proc. ICASSP-2000, Istanbul, II-1117-1120. (4pp)

D. Genoud, D. Ellis and N. Morgan (1999). Combined speech and speaker recognition with speaker-adapted connectionist models
Proc. Auto. Speech Recog. & Understanding Workshop, Keystone. (4pp)

D. Abberley, S. Renals, T. Robinson and D. Ellis (1999). The THISL SDR system at TREC-8
Proc. Text Retrieval Conference 8, Washington. (6pp)

G. Williams and D. Ellis (1999). Speech/music discrimination based on posterior probability features
Proc. Eurospeech-99, Budapest. (4 pp)

A. Janin, D. Ellis and N. Morgan (1999). Multi-stream speech recognition: Ready for prime time?
Proc. Eurospeech-99, Budapest. (4 pp)

D.P.W. Ellis and N. Morgan (1999). Size matters: An empirical study of neural network training for large vocabulary continuous speech recognition
Proc. ICASSP-99, Phoenix. (4 pp)

N. Morgan, D. Ellis, E. Fosler-Lussier, A. Janin and B. Kingsbury (1999). Reducing errors by increasing the error rate: MLP Acoustic Modeling for Broadcast News Transcription
Presented at the DARPA Broadcast News Transcription and Understanding Workshop, Gaithersburg VA, 1999feb28. (4pp)

G. Cook, J. Christie, D. Ellis, E. Fosler-Lussier, Y. Gotoh, B. Kingsbury, N. Morgan, S. Renals, T. Robinson and G. Williams (1999). The SPRACH System for the Transcription of Broadcast News
Presented at the DARPA Broadcast News Transcription and Understanding Workshop, Gaithersburg VA, 1999feb28. (4pp)

D.P.W. Ellis(1999?). Modeling the auditory organization of speech - a summary and some comments
Chapter prepared for Listening to speech: An auditory perspective, S. Greenberg & W. Ainsworth, eds., Oxford University Press, to appear. (13pp)

M. Cooke and D.P.W. Ellis (2001). The auditory organization of speech and other sources in listeners and computational models
Speech Communication, accepted for publication (37pp)

D.P.W. Ellis (1999). Using knowledge to organize sound: The prediction-driven approach to computational auditory scene analysis, and its application to speech/nonspeech mixtures
Speech Communication special issue on Computational Auditory Scene Analysis, M. Cooke & H. Okuno, eds. (11pp)

D.P.W. Ellis (1998?). Speech recognition as a component in computational auditory scene analysis
Unpublished monograph. (4pp)

D.P.W. Ellis (1997). The Weft: A representation for periodic sounds
Proc. Int. Conf. on Acous., Speech & Sig. Proc. ICASSP-97, Munich, vol. 2 pp. 1307-1310, April 1997. (4pp)

D.P.W. Ellis (1997). Computational Auditory Scene Analysis exploiting Speech-Recognition knowledge
Proc. IEEE Workshop on Apps. of Sig. Proc. to Acous. and Audio, Mohonk, October 1997. (4pp)

D.P.W. Ellis (1996). Prediction-driven computational auditory scene analysis for dense sound mixtures
Proc. ESCA Workshop on the Auditory Basis of Speech Perception, Keele, July 1996. (6pp)

D.P.W. Ellis (1996). Prediction-driven computational auditory scene analysis (also in Acrobat PDF)
Ph.D. thesis, Dept. of Elec. Eng & Comp. Sci., M.I.T., June 1996. (180pp)

D.P.W. Ellis (1995). Underconstrained stochastic representations for top-down computational auditory scene analysis
Proc. IEEE Workshop on Apps. of Sig. Proc. to Acous. and Audio, Mohonk, October 1995. (4pp)

D.P.W. Ellis (1995). Hard problems in computational auditory scene analysis
Posted to the AUDITORY email list, August 1995. (4pp)

D.P.W. Ellis and D.F Rosenthal (1995). Mid-level representations for Computational Auditory Scene Analysis
Proc. Intl. Joint Conf. on Artif. Intell. Workshop on Computational Auditory Scene Analysis, Montreal, August 1995. (7pp)

D.P.W. Ellis (1994). A computer implementation of psychoacoustic grouping rules
Proc. 12th Intl. Conf. on Pattern Recognition, Jerusalem, October 1994. (9pp)

D.P.W. Ellis (1993). Vowel separation by glottal-pulse synchrony
Presented to the 126th meeting of the Acoustical Society of America, Denver, November 1993. (17pp)

D.P.W. Ellis (1993). Hierarchic models of sound for separation and restoration
Proc. 1993 IEEE Mohonk workshop on Applications of Signal Processing to Acoustics and Audio, October 1993. (4pp)

D.P.W. Ellis and B.L. Vercoe (1992). A perceptual representation of sound for auditory signal separation
Presented to the 123rd meeting of the Acoustical Society of America, Salt Lake City, May 1992. (8pp)

D.P.W. Ellis (1992). A Perceptual Representation of Audio (also in Acrobat PDF)
Master's thesis, EECS dept, MIT, February 1992. (88pp)

[ Dan's research ] [ Dan Ellis ] [ ICSI Realization group ]


Updated: $Date: 2001/05/17 19:21:23 $
DAn Ellis <dpwe@icsi.berkeley.edu>
International Computer Science Institute, Berkeley CA