Algorithmic composition of melodies with deep recurrent neural networks

A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated mu- sic composers able to generate new melodies coherent with the style they have been trained on. We employ gated-recurrent unit (GRU) networks that have been shown to be particularly efficient in learning complex sequential activations with arbitrary long time lags. Our model processes rhythm and melody in parallel while modeling the relation between these two properties. Using such an approach, we were able to generate interesting complete melodies or suggest possible continuations of a melody fragment that is coherent with the characteristics of the fragment itself.


    Poster associated with the conference article of the same name. It was presented at the Machine Learning Summer School (MLSS) 2016 and during the special poster session of AISTATS 2016 in Cadiz, Spain.


    • EPFL-POSTER-225481

    Record created on 2017-02-01, modified on 2017-05-12

Related material