Research Scientist, Google, Inc., New York City
Professor, Electrical Engineering, Columbia University
PI, Lab for Recognition and Organization of Speech and Audio (LabROSA)
Dan Ellis does research and development in the area of signal processing and machine learning applied to extracting information from sound.
From 2000 to 2015, he ran LabROSA at Columbia University, leading research into: speech, environmental audio, music recordings, and marine mammal sounds (see the Research Overview).
Ellis graduated from MIT where he was a research assistant in the Machine Listening Group of the Media Lab. He spent several years as a research scientist at the International Computer Science Institute (affiliated with UC Berkeley).
CV: Full or 2-page
Contact info / Directions
Laboratory for Recognition and Organization of Speech and Audio (LabROSA)
Teaching + Materials
ELEN E4896 - Music Signal Processing (Spring 2014)
EECS E6891 - Reproducing Computational Results (Spring 2014)
ELEN E4810 - Digital Signal Processing (Summer 2015)
ELEN E6820 - Speech and Audio Processing and Recognition (Spring 2009)
Music Engineering Art Projects
Short Course on Music Content Analysis by Machine Learning
Student info: Bulletin, Signals Roadmap, Undergrad checklist, 3-2 Course Equivalency Form
The Listening Machine
Separating Speech in Complex Environments
Novel Speech Features
Personal Audio Analysis
Music Content Analysis (Melody transcription, Music similarity)
Marine Mammal Sounds
Live Spectrogram for "Machines Listening to Music"
Matlab Audio Processing Examples
Sound Examples for Projects
Workshops (CRAC01,SAPA 04,06,08,10,12, ISMIR-08 etc.)
EESIP Seminar Series
Other local resources...