Abstract
In the previous decade, Deep Learning (DL) has proven to be one of the most effective machine learning methods to tackle a wide range of Music Information Retrieval (MIR) tasks. It offers highly expressive learning capacity that can fit any music representation needed for MIR-relevant downstream tasks. However, it has been criticized for sacrificing interpretability. On the other hand, the Bayesian nonparametric (BN) approach promises similar positive properties as DL, such as high flexibility, while being robust to overfitting and preserving interpretability. Therefore, the primary motivation of this work is to explore the potential of Bayesian nonparametric models in comparison to DL models for music representation learning. More specifically, we assess the music representation learned from the Hierarchical Dirichlet Process Gaussian Mixture Model (HDPGMM), an infinite mixture model based on the Bayesian nonparametric approach, to MIR tasks, including classification, auto-tagging, and recommendation. The experimental result suggests that the HDPGMM music representation can outperform DL representations in certain scenarios, and overall comparable.
Original language | English |
---|---|
Title of host publication | Proceedings of the 23rd International Society for Music Information Retrieval Conference |
Pages | 116 - 124 |
Number of pages | 9 |
Publication status | Published - 2022 |
Event | 23rd International Society for Music Information Retrieval Conference - Bengaluru, India Duration: 4 Dec 2022 → 8 Dec 2022 Conference number: 23 |
Conference
Conference | 23rd International Society for Music Information Retrieval Conference |
---|---|
Abbreviated title | ISMIR 2022 |
Country/Territory | India |
City | Bengaluru |
Period | 4/12/22 → 8/12/22 |
Fingerprint
Dive into the research topics of 'The power of deep without going deep? A study of HDPGMM music representation learning'. Together they form a unique fingerprint.Datasets
-
Supplementary material of the paper "The power of deep without going deep? A study of HDPGMM music representation learning"
Kim, J. H. (Creator) & Liem, C. C. S. (Creator), TU Delft - 4TU.ResearchData, 6 Feb 2023
DOI: 10.4121/21981442
Dataset/Software: Dataset