The thesis defence "Representation Learning for Symbolic Music" will be held on the 7th of June, at 2.30 PM
Mathieu Prang will defend his thesis directed by Philippe Esling and Carlos Agon, in English,
Jury :
Frederic Bimbot : Université Rennes
Anna Jordanous : Kent university
Geoffroy Peeters : Telecom ParisTech
Jean-Pierre Briot : Sorbonne Université
Florence Levé : Université de Picardie Jules Verne
Simon Colton : Goldsmith university
abstract :
A key part in the recent success of deep language processing models lies in the ability to learn efficient word embeddings. These methods provide structured spaces
of reduced dimensionality with interesting metric relationship properties. These, in turn, can be used as efficient input representations for handling more complex
tasks. In this thesis, we focus on the task of learning embedding spaces for polyphonic music in the symbolic domain. To do so, we explore two different approaches. The first one is inspired by the work done in the Natural Language Processing (NLP) field and relies on prediction tasks, while the second is based on the latent space of Variational Auto-Encoders (VAE).