Enhancing Music Features by Knowledge Transfer from User-item Log Data

In this paper, we propose a novel method that exploits music listening log data for general-purpose music feature extraction. Despite the wealth of information available in the log data of user-item interactions, it has been mostly used for collaborative filtering to find similar items or users and...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 386 - 390
Main Authors Lee, Donmoon, Lee, Jaejun, Park, Jeongsoo, Lee, Kyogu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2019
Subjects
Data models
Feature extraction
knowledge distillation
Knowledge transfer
Matrix converters
Music feature extraction
neural networks
Recommender systems
Task analysis
Training
user-item log
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a novel method that exploits music listening log data for general-purpose music feature extraction. Despite the wealth of information available in the log data of user-item interactions, it has been mostly used for collaborative filtering to find similar items or users and was not fully investigated for content-based music applications. We resolve this problem by extending intra-domain knowledge distillation to cross-domain: i.e., by transferring knowledge obtained from the user-item domain to the music content domain. The proposed system first trains the model that estimates log information from the audio contents; then it uses the model to improve other task-specific models. The experiments on various music classification and regression tasks show that the proposed method successfully improves the performances of the task-specific models.
ISSN:2379-190X
DOI:10.1109/ICASSP.2019.8682345