Embedding-based Music Emotion Recognition Using Composite Loss
This work addresses the challenge of modeling subjective emotional variations in music for applications in music recommendation and analysis, representing an incremental improvement over existing classification or regression methods.
The paper tackled the problem of music emotion recognition by proposing an embedding-based approach that captures both general emotional categories and fine-grained variations within them, achieving robust bidirectional recognition on two benchmark datasets.
Most music emotion recognition approaches perform classification or regression that estimates a general emotional category from a distribution of music samples, but without considering emotional variations (e.g., happiness can be further categorised into much, moderate or little happiness). We propose an embedding-based music emotion recognition approach that associates music samples with emotions in a common embedding space by considering both general emotional categories and fine-grained discrimination within each category. Since the association of music samples with emotions is uncertain due to subjective human perceptions, we compute composite loss-based embeddings obtained to maximise two statistical characteristics, one being the correlation between music samples and emotions based on canonical correlation analysis, and the other being a probabilistic similarity between a music sample and an emotion with KL-divergence. The experiments on two benchmark datasets demonstrate the effectiveness of our embedding-based approach, the composite loss and learned acoustic features. In addition, detailed analysis shows that our approach can accomplish robust bidirectional music emotion recognition that not only identifies music samples matching with a specific emotion but also detects emotions expressed in a certain music sample.