Saved in:
Bibliographic Details
Main Authors: Ching, Joann, Widmer, Gerhard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.04688
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914155583242240
author Ching, Joann
Widmer, Gerhard
author_facet Ching, Joann
Widmer, Gerhard
contents Music Emotion Recognition (MER) is a task deeply connected to human perception, relying heavily on subjective annotations collected from contributors. Prior studies tend to focus on specific musical styles rather than incorporating a diverse range of genres, such as rock and classical, within a single framework. In this paper, we address the task of recognizing emotion from audio content by investigating five datasets with dimensional emotion annotations -- EmoMusic, DEAM, PMEmo, WTC, and WCMED -- which span various musical styles. We demonstrate the problem of out-of-distribution generalization in a systematic experiment. By closely looking at multiple data and feature sets, we provide insight into genre-emotion relationships in existing data and examine potential genre dominance and dataset biases in certain feature representations. Based on these experiments, we arrive at a simple yet effective framework that combines embeddings extracted from the Jukebox model with chroma features and demonstrate how, alongside a combination of several diverse training sets, this permits us to train models with substantially improved cross-dataset generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04688
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Study on the Data Distribution Gap in Music Emotion Recognition
Ching, Joann
Widmer, Gerhard
Sound
Machine Learning
Music Emotion Recognition (MER) is a task deeply connected to human perception, relying heavily on subjective annotations collected from contributors. Prior studies tend to focus on specific musical styles rather than incorporating a diverse range of genres, such as rock and classical, within a single framework. In this paper, we address the task of recognizing emotion from audio content by investigating five datasets with dimensional emotion annotations -- EmoMusic, DEAM, PMEmo, WTC, and WCMED -- which span various musical styles. We demonstrate the problem of out-of-distribution generalization in a systematic experiment. By closely looking at multiple data and feature sets, we provide insight into genre-emotion relationships in existing data and examine potential genre dominance and dataset biases in certain feature representations. Based on these experiments, we arrive at a simple yet effective framework that combines embeddings extracted from the Jukebox model with chroma features and demonstrate how, alongside a combination of several diverse training sets, this permits us to train models with substantially improved cross-dataset generalization capabilities.
title A Study on the Data Distribution Gap in Music Emotion Recognition
topic Sound
Machine Learning
url https://arxiv.org/abs/2510.04688