COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Trinity Mathematical Society > Deep learning for music recommendation and generation
Deep learning for music recommendation and generationAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Michelle Sweering. This is a joint talk with the Trinity College Science Society. Please note the unusual time. The advent of deep learning has made it possible to extract high-level information from perceptual signals without having to specify manually and explicitly how to obtain it; instead, this can be learned from examples. This creates opportunities for automated content analysis of musical audio signals. In this talk, I will discuss how deep learning techniques can be used for audio-based music recommendation. I will also briefly discuss my ongoing work on music generation with WaveNet. This talk is part of the Trinity Mathematical Society series. This talk is included in these lists:Note that ex-directory lists are not shown. |
Other listsLogic and Semantics Seminar (Computer Laboratory) Beyond Profit Institute for Energy and Environmental Flows (IEEF) Institute of Theoretical Geophysics Informal Lunchtime Seminars (DAMTP) Engineering Department Energy, Fluids and Thermo seminarsOther talksIdentifying new gene regulating networks in immune cells Poison trials, panaceas and proof: debates about testing and testimony in early modern European medicine Designing Active Macroscopic Heat Engines Mothers & Daughters: a psychoanalytical perspective C++11/14 - the new C++ Statistical Methods in Pre- and Clinical Drug Development: Tumour Growth-Inhibition Model Example |