Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
This work addresses a specific bottleneck in symbolic music emotion recognition for music AI applications, representing an incremental improvement over existing pre-trained models.
The paper tackles the problem that existing symbolic music emotion recognition models overlook tonal structures like musical modes, which are critical for emotional perception according to music psychology. By proposing a Mode-Guided Enhancement strategy that injects explicit mode features into MIDIBERT, the method achieves accuracies of 75.2% and 59.1% on EMOPIA and VGMIDI datasets, significantly improving performance.
Music emotion recognition is a key task in symbolic music understanding (SMER). Recent approaches have shown promising results by fine-tuning large-scale pre-trained models (e.g., MIDIBERT, a benchmark in symbolic music understanding) to map musical semantics to emotional labels. While these models effectively capture distributional musical semantics, they often overlook tonal structures, particularly musical modes, which play a critical role in emotional perception according to music psychology. In this paper, we investigate the representational capacity of MIDIBERT and identify its limitations in capturing mode-emotion associations. To address this issue, we propose a Mode-Guided Enhancement (MoGE) strategy that incorporates psychological insights on mode into the model. Specifically, we first conduct a mode augmentation analysis, which reveals that MIDIBERT fails to effectively encode emotion-mode correlations. We then identify the least emotion-relevant layer within MIDIBERT and introduce a Mode-guided Feature-wise linear modulation injection (MoFi) framework to inject explicit mode features, thereby enhancing the model's capability in emotional representation and inference. Extensive experiments on the EMOPIA and VGMIDI datasets demonstrate that our mode injection strategy significantly improves SMER performance, achieving accuracies of 75.2% and 59.1%, respectively. These results validate the effectiveness of mode-guided modeling in symbolic music emotion recognition.