
Deep content-based music recommendation
- Author
- Aäron van den Oord (UGent) , Sander Dieleman (UGent) and Benjamin Schrauwen (UGent)
- Organization
- Abstract
- Automatic music recommendation has become an increasingly relevant problem in recent years, since a lot of music is now sold and consumed digitally. Most recommender systems rely on collaborative filtering. However, this approach suffers from the cold start problem: it fails when no usage data is available, so it is not effective for recommending new and unpopular songs. In this paper, we propose to use a latent factor model for recommendation, and predict the latent factors from music audio when they cannot be obtained from usage data. We compare a traditional approach using a bag-of-words representation of the audio signals with deep convolutional neural networks, and evaluate the predictions quantitatively and qualitatively on the Million Song Dataset. We show that using predicted latent factors produces sensible recommendations, despite the fact that there is a large semantic gap between the characteristics of a song that affect user preference and the corresponding audio signal. We also show that recent advances in deep learning translate very well to the music recommendation setting, with deep convolutional neural networks significantly outperforming the traditional approach.
- Keywords
- content-based recommendation, convolutional neural networks, recommender systems, deep learning, music recommendation
Downloads
-
5004-deep-content-based-music-recommendation.pdf
- full text
- |
- open access
- |
- |
- 893.80 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-4324554
- MLA
- van den Oord, Aäron, et al. “Deep Content-Based Music Recommendation.” Advances in Neural Information Processing Systems 26 (2013), edited by Christopher Burges et al., vol. 26, Neural Information Processing Systems Foundation (NIPS), 2013.
- APA
- van den Oord, A., Dieleman, S., & Schrauwen, B. (2013). Deep content-based music recommendation. In C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Weinberger (Eds.), Advances in Neural Information Processing Systems 26 (2013) (Vol. 26). Lake Tahoe, NV, USA: Neural Information Processing Systems Foundation (NIPS).
- Chicago author-date
- Oord, Aäron van den, Sander Dieleman, and Benjamin Schrauwen. 2013. “Deep Content-Based Music Recommendation.” In Advances in Neural Information Processing Systems 26 (2013), edited by Christopher Burges, Léon Bottou, Max Welling, Zoubin Ghahramani, and Kilian Weinberger. Vol. 26. Lake Tahoe, NV, USA: Neural Information Processing Systems Foundation (NIPS).
- Chicago author-date (all authors)
- van den Oord, Aäron, Sander Dieleman, and Benjamin Schrauwen. 2013. “Deep Content-Based Music Recommendation.” In Advances in Neural Information Processing Systems 26 (2013), ed by. Christopher Burges, Léon Bottou, Max Welling, Zoubin Ghahramani, and Kilian Weinberger. Vol. 26. Lake Tahoe, NV, USA: Neural Information Processing Systems Foundation (NIPS).
- Vancouver
- 1.van den Oord A, Dieleman S, Schrauwen B. Deep content-based music recommendation. In: Burges C, Bottou L, Welling M, Ghahramani Z, Weinberger K, editors. Advances in Neural Information Processing Systems 26 (2013). Lake Tahoe, NV, USA: Neural Information Processing Systems Foundation (NIPS); 2013.
- IEEE
- [1]A. van den Oord, S. Dieleman, and B. Schrauwen, “Deep content-based music recommendation,” in Advances in Neural Information Processing Systems 26 (2013), Lake Tahoe, NV, USA, 2013, vol. 26.
@inproceedings{4324554, abstract = {{Automatic music recommendation has become an increasingly relevant problem in recent years, since a lot of music is now sold and consumed digitally. Most recommender systems rely on collaborative filtering. However, this approach suffers from the cold start problem: it fails when no usage data is available, so it is not effective for recommending new and unpopular songs. In this paper, we propose to use a latent factor model for recommendation, and predict the latent factors from music audio when they cannot be obtained from usage data. We compare a traditional approach using a bag-of-words representation of the audio signals with deep convolutional neural networks, and evaluate the predictions quantitatively and qualitatively on the Million Song Dataset. We show that using predicted latent factors produces sensible recommendations, despite the fact that there is a large semantic gap between the characteristics of a song that affect user preference and the corresponding audio signal. We also show that recent advances in deep learning translate very well to the music recommendation setting, with deep convolutional neural networks significantly outperforming the traditional approach.}}, author = {{van den Oord, Aäron and Dieleman, Sander and Schrauwen, Benjamin}}, booktitle = {{Advances in Neural Information Processing Systems 26 (2013)}}, editor = {{Burges, Christopher and Bottou, Léon and Welling, Max and Ghahramani, Zoubin and Weinberger, Kilian}}, isbn = {{9781632660244}}, keywords = {{content-based recommendation,convolutional neural networks,recommender systems,deep learning,music recommendation}}, language = {{eng}}, location = {{Lake Tahoe, NV, USA}}, pages = {{9}}, publisher = {{Neural Information Processing Systems Foundation (NIPS)}}, title = {{Deep content-based music recommendation}}, url = {{http://papers.nips.cc/paper/5004-deep-content-based-music-recommendation.pdf}}, volume = {{26}}, year = {{2013}}, }