Predictive models for music - Archive ouverte HAL Access content directly
Journal Articles Connection Science Year : 2009

Predictive models for music


Modelling long-term dependencies in time series has proved very difficult to achieve with traditional machine-learning methods. This problem occurs when considering music data. In this paper, we introduce predictive models for melodies. We decompose melodic modelling into two subtasks. We first propose a rhythm model based on the distributions of distances between subsequences. Then, we define a generative model for melodies given chords and rhythms based on modelling sequences of Narmour features. The rhythm model consistently outperforms a standard hidden markov model (HMM) in terms of conditional prediction accuracy on two different music databases. Using a similar evaluation procedure, the proposed melodic model consistently outperforms an input/output HMM. Furthermore, these models are able to generate realistic melodies given appropriate musical contexts.

Dates and versions

hal-00416135 , version 1 (11-09-2009)



Jean-François Paiement, Yves Grandvalet, Samy Bengio. Predictive models for music. Connection Science, 2009, 21 (2-3), pp.253-272. ⟨10.1080/09540090902733806⟩. ⟨hal-00416135⟩
53 View
0 Download



Gmail Facebook Twitter LinkedIn More