Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning

Tran S, Wolff D, Weyde T, Garcez AD. Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning. In: AES Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society; 2014. Paper P1-4. Available from: https://aes.org/publications/elibrary-page/?id=17107

@inproceedings{Tran2014_17107,
  author = {Tran, Son and Wolff, Daniel and Weyde, Tillman and Garcez, Artur d'Avila},
  title = {{Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning}},
  booktitle = {AES Conference: 53rd International Conference: Semantic Audio},
  note = {Paper P1-4},
  year = {2014},
  month = jan,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17107}
}

TY  - CPAPER
TI  - Feature Preprocessing with Restricted Boltzmann Machines for Music Similarity Learning
AU  - Tran, Son
AU  - Wolff, Daniel
AU  - Weyde, Tillman
AU  - Garcez, Artur d'Avila
T2  - AES Conference: 53rd International Conference: Semantic Audio
M1  - Paper P1-4
PY  - 2014
DA  - 2014/01/06
UR  - https://aes.org/publications/elibrary-page/?id=17107
PB  - Audio Engineering Society
LA  - en
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.
ER  -