@inproceedings{787b6844e49e47679f42cb100bced9a5,
title = "Comparing Probabilistic Models for Melodic Sequences",
abstract = "Modelling the real world complexity of music is a challenge for machine learning. We address the task of modeling melodic sequences from the same music genre. We perform a comparative analysis of two probabilistic models; a Dirichlet Variable Length Markov Model (Dirichlet-VMM) and a Time Convolutional Restricted Boltzmann Machine (TC-RBM). We show that the TC-RBM learns descriptive music features, such as underlying chords and typical melody transitions and dynamics. We assess the models for future prediction and compare their performance to a VMM, which is the current state of the art in melody generation. We show that both models perform significantly better than the VMM, with the Dirichlet-VMM marginally outperforming the TC-RBM. Finally, we evaluate the short order statistics of the models, using the Kullback-Leibler divergence between test sequences and model samples, and show that our proposed methods match the statistics of the music genre significantly better than the VMM.",
keywords = "melody modeling, music feature extraction, time convolutional restricted Boltzmann machine, variable length Markov model, Dirichlet prior, LEARNING ALGORITHM",
author = "Athina Spiliopoulou and Amos Storkey",
year = "2011",
doi = "10.1007/978-3-642-23808-6_19",
language = "English",
isbn = "978-3-642-23807-9",
series = "Lecture Notes in Artificial Intelligence",
publisher = "Springer",
pages = "289--304",
editor = "D Gunopulos and T Hofmann and D Malerba and M Vazirgiannis",
booktitle = "MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, PT III",
address = "United Kingdom",
note = "European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) ; Conference date: 05-09-2011 Through 09-09-2011",
}