Memo2496: Expert-Annotated Dataset and Dual-View Adaptive Framework for Music Emotion Recognition

TL;DR

This paper introduces Memo2496, a high-quality annotated music emotion dataset, and DAMER, a dual-view adaptive framework that improves music emotion recognition by addressing feature drift and leveraging multi-modal data.

Contribution

The work presents a large-scale, expert-annotated dataset and a novel dual-view adaptive model with three modules, advancing the accuracy and robustness of music emotion recognition.

Findings

DAMER achieves state-of-the-art performance on multiple datasets.

The dataset ensures high annotation quality through calibration and consistency checks.

Each module of DAMER significantly contributes to performance improvements.

Abstract

Music Emotion Recogniser (MER) research faces challenges due to limited high-quality annotated datasets and difficulties in addressing cross-track feature drift. This work presents two primary contributions to address these issues. Memo2496, a large-scale dataset, offers 2496 instrumental music tracks with continuous valence arousal labels, annotated by 30 certified music specialists. Annotation quality is ensured through calibration with extreme emotion exemplars and a consistency threshold of 0.25, measured by Euclidean distance in the valence arousal space. Furthermore, the Dual-view Adaptive Music Emotion Recogniser (DAMER) is introduced. DAMER integrates three synergistic modules: Dual Stream Attention Fusion (DSAF) facilitates token-level bidirectional interaction between Mel spectrograms and cochleagrams via cross attention mechanisms; Progressive Confidence Labelling (PCL) generates reliable pseudo labels employing curriculum-based temperature scheduling and consistency quantification using Jensen Shannon divergence; and Style Anchored Memory Learning (SAML) maintains a contrastive memory queue to mitigate cross-track feature drift. Extensive experiments on the Memo2496, 1000songs, and PMEmo datasets demonstrate DAMER's state-of-the-art performance, improving arousal dimension accuracy by 3.43%, 2.25%, and 0.17%, respectively. Ablation studies and visualisation analyses validate each module's contribution. Both the dataset and source code are publicly available.