AES E-Library

S. Tran, D. Wolff, T. Weyde, and AR. D'. Garcez, "Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning," Paper P1-4, (2014 January.). doi: S. Tran, D. Wolff, T. Weyde, and AR. D'. Garcez, "Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning," Paper P1-4, (2014 January.). doi:
Abstract: Computational modelling of music similarity constitutes a key element for music information retrieval and recommendation systems. Similarity models and their analysis are also important for research in musicology and music perception. In this study, we test feature preprocessing with Restricted Boltzmann Machines in combination with established methods for learning distance measures. Our experiments show that this preprocessing improves the overall generalisation results of the trained models. We compare the effects of feature preprocessing on distance function learning using gradient ascent and support vector machines. The evaluation is performed using similarity data from the MagnaTagATune dataset, which allows a comparison of our results with previous studies.

@article{tran2014feature,
author={tran, son and wolff, daniel and weyde, tillman and garcez, artur d'avila},
journal={journal of the audio engineering society},
title={feature preprocessing with restricted boltzmann machines for music similarity learning},
year={2014},
volume={},
number={},
pages={},
doi={},
month={january},} @article{tran2014feature,
author={tran, son and wolff, daniel and weyde, tillman and garcez, artur d'avila},
journal={journal of the audio engineering society},
title={feature preprocessing with restricted boltzmann machines for music similarity learning},
year={2014},
volume={},
number={},
pages={},
doi={},
month={january},
abstract={computational modelling of music similarity constitutes a key element for music information retrieval and recommendation systems. similarity models and their analysis are also important for research in musicology and music perception. in this study, we test feature preprocessing with restricted boltzmann machines in combination with established methods for learning distance measures. our experiments show that this preprocessing improves the overall generalisation results of the trained models. we compare the effects of feature preprocessing on distance function learning using gradient ascent and support vector machines. the evaluation is performed using similarity data from the magnatagatune dataset, which allows a comparison of our results with previous studies.},}

TY - paper
TI - Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning
SP - EP -
AU - Tran, Son
AU - Wolff, Daniel
AU - Weyde, Tillman
AU - Garcez, Artur d'Avila
PY - 2014
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - January 2014 TY - paper
TI - Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning
SP - EP -
AU - Tran, Son
AU - Wolff, Daniel
AU - Weyde, Tillman
AU - Garcez, Artur d'Avila
PY - 2014
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - January 2014
AB - Computational modelling of music similarity constitutes a key element for music information retrieval and recommendation systems. Similarity models and their analysis are also important for research in musicology and music perception. In this study, we test feature preprocessing with Restricted Boltzmann Machines in combination with established methods for learning distance measures. Our experiments show that this preprocessing improves the overall generalisation results of the trained models. We compare the effects of feature preprocessing on distance function learning using gradient ascent and support vector machines. The evaluation is performed using similarity data from the MagnaTagATune dataset, which allows a comparison of our results with previous studies.