Gregory Sell
gsell (at) ccrma (dot) stanford (dot) edu

---

Education

• PhD in Computer-Based Music Theory and Acoustics, Stanford University (CCRMA), January 2011
• Master of Science in Electrical Engineering, Stanford University, 2007
• Master of Arts in Music, Stanford University (CCRMA), 2005
• Bachelor of Arts in Music, Stanford University, 2005

Research Interests

• Speaker Diarization
• Speaker Recognition
• Language Recognition
• Source Separation and Enhancement
• Multimedia Processing
• Audio Search, Similarity, and Organization
• Audio Demodulation LINK
• Diffusion Mapping LINK
• Graph Processing
• Auditory Perception
• Speech Activity Detection
• Music Recommendation
• Music Information Retrieval
• Data Sonification

Dissertation

My dissertation work examined the capabilities of diffusion mapping for visualizing and analyzing the geometries inherent in music and music theory. More information on the research, a copy of the dissertation, and links to the accompanying animations can all be found HERE.

Publications (I have largely stopped updating this list - a SCHOLAR SEARCH will include my recent publications.)

• Gregory Sell, Clara Suied, Mounya Elhilali, and Shihab Shamma, Perceptual Susceptibility to Acoustic Manipulations in Speaker Discrimination, Journal of the Acoustical Society of America, 137(2): 911-922, 2015. DOWNLOAD
  
  Copyright 2015 Acoustical Society of America. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America. The article may be found HERE.


• Gregory Sell, Optimizing Coherent Demodulation for Improved Separation of Overlapping Sources, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vancouver, Canada, 2013. DOWNLOAD


• Pascal Clark, Gregory Sell, and Les Atlas, A Novel Approach Using Modulation Features for Multiphone-Based Speech Recognition, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Prague, Czech Republic, 2011. DOWNLOAD


• Geoffrey Zweig, Patrick Nguyen, Dirk Van Compernolle, Kris Demuynck, Les Atlas, Pascal Clark, Greg Sell, Fei Sha, Meihong Wang, Aren Jansen, Hynek Hermansky, Damianos Karakos, Keith Kintzley, Samuel Thomas, Sivaram GSVS, Sam Bowman, and Justine Kao, Speech recogntion with segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, 2011. DOWNLOAD


• Geoffrey Zweig, Patrick Nguyen, Dirk Van Compernolle, Kris Demuynck, Les Atlas, Pascal Clark, Greg Sell, Fei Sha, Meihong Wang, Aren Jansen, Hynek Hermansky, Damianos Karakos, Keith Kintzley, Samuel Thomas, Sivaram GSVS, Sam Bowman, and Justine Kao, Speech Recognition with Segmental Conditional Random Fields: Final Report for the 2010 JHU Summer Workshop, Johns Hopkins University, 2010. DOWNLOAD


• Gregory Sell and Malcolm Slaney, The Information Content of Demodulated Speech, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, USA, 2010. DOWNLOAD


• Gregory Sell and Malcolm Slaney, Solving Demodulation as an Optimization Problem, IEEE Transactions on Audio, Speech and Language Processing, 18(8):2051-2066, Nov 2010. DOWNLOAD


• Kyogu Lee, Gregory Sell, and Jonathan Berger, Sonification Using Digital Waveguides and 2- and 3-Dimensional Digital Waveguide Mesh, Proceedings of the International Conference on Auditory Display, Limerick, Ireland, 2005. DOWNLOAD

(And from my pre-med days...)
• Anton E. Dmitriev, Bryan W. Cunningham, Nianbin Hu, Gregory Sell, Franco Vigna, and Paul C. McAfee, Adjacent Level Intradiscal Pressure and Segmental Kinematics Following a Cervical Total Disc Anthroplasty: An In Vitro Human Cadaveric Model, Spine, 30(10):1165-1172, May 2005.