Bio

Thierry Bertin-Mahieux

titi.jpg

Thierry Bertin-Mahieux is a tech entrepreneur in the AI+Retail space. He is the co-founder / CTO of Singuli, a modern commerce decision platform.

He previously started the data science team at Oyster, then worked for Google NYC and YouTube Paris. He holds a PhD from Columbia University (topic: machine learning for audio) and an Executive MBA from INSEAD. He's interested in everything related to applied AI, especially when deployed to more traditional industries.

 

WORK

Co-founder / CTO - Singuli, 2019-

Software Engineer - YouTube, Google, Paris France, 2016-2019

Software Engineer - Play Books, Google, New York NY, 2015-2016

Director of Data Science - Oyster, New York NY, 2014-2015

Data Scientist - Birchbox, New York NY, 2013-2014

Intern - Google, New York NY, 2012

Intern - The Echo Nest, Somerville MA, 2011

Intern - IREQ, Quebec, CAN, 2009

Intern - Sun Microsystems, Burlington MA, 2007


EDUCATION

Executive MBA, INSEAD

Ph.D. Electrical Engineering, Columbia University

M.Sc. Computer Science, University of Montreal

B.Sc. Mathematics, University of Montreal


PUBLICATIONS

T. Bertin-Mahieux, 
Large-Scale Pattern Discovery in Music, Ph.D. thesis, Columbia University, 2013.
[pdf][bib]

T. Bertin-Mahieux and D. Ellis,
Large-scale cover song recognition using the 2D Fourier transform magnitude, In Proceedings of the 13th International Conference on Music Information Retrieval (ISMIR), 2012.
[pdf] [bib]

B. McFee, T. Bertin-Mahieux, D. Ellis and G. Lanckriet, 
The Million Song Dataset Challenge, In Proceedings of the 4th International Workshop on Advances in Music Information Research (AdMIRe ’12), 2012.
[pdf] [bib] [web]

T. Bertin-Mahieux, D. Ellis, B. Whitman and P. Lamere, 
The Million Song Dataset, In Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR), 2011.
[pdf] [bib] [dataset] [code]

T. Bertin-Mahieux and D. Ellis,
Large-scale cover song recognition using hashed chroma landmarks, In Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2011.
[pdf] [bib] (Best Paper Nominee)

T. Bertin-Mahieux, G. Grindlay, R. Weiss and D. Ellis,
Evaluating music sequence models through missing data, In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2011.
[pdf] [bib]

T. Bertin-Mahieux, R. Weiss and D. Ellis, 
Clustering beat-chroma patterns in a large music database, In Proceedings of the 11th International Conference on Music Information Retrieval (ISMIR), 2010.
[pdf] [bib] [poster]

T. Bertin-Mahieux, D. Eck and M. Mandel, 
Automatic tagging of audio: The state-of-the-art. In Wenwu Wang, editor, Machine Audition: Principles, Algorithms and Systems. IGI Publishing, 2010.
[amazon] [draft] [bib]

T. Bertin-Mahieux.
Apprentissage statistique pour l’étiquetage de musique et la recommandation. M.Sc. thesis, University of Montreal.
[pdf] (in French)

P.-A. Manzagol, T. Bertin-Mahieux and D. Eck.
On the use of sparse time relative auditory codes for music. In Proceedings of the 9th International Conference on Music Information Retrieval (ISMIR), 2008.
[pdf] [bib(Best Student Paper Award)

T. Bertin-Mahieux, D. Eck, F. Maillet and P. Lamere,
Autotagger: a model for predicting social tags from acoustic features on large music databases. In Journal of New Music Research, special issue: ”From genres to tags: Music Information Retrieval in the era of folksonomies.“, 37(2):151–165, 2008.
[journal] [draft] [bib]

B. Kégl, T. Bertin-Mahieux and D. Eck,
Metropolis-Hastings sampling in a FilterBoost music classifier, at International Workshop on Machine Learning and Music (ICML08 Workshop), 2008.
[pdf] [slides] [video] [bib]

D. Eck, P. Lamere, T. Bertin-Mahieux and S. Green. 
Automatic generation of social tags for music recommendation. In Neural Information Processing Systems Conference (NIPS) 20, 2007.
[pdf] [bib] [code]

D. Eck, T. Bertin-Mahieux and P. Lamere.
Autotagging music using supervised machine learning. In Proceedings of the 8th International Conference on Music Information Retrieval (ISMIR), 2007.
[pdf] [longer submission] [bib]