RESEARCH

HOME RESEARCH
Multimedia Modeling
Affect
Content Analysis
A Genre-Affect Relationship Network with Task-Specific Uncertainty Weighting foR Recognizing Induced Emotion in Music
Abstract
Emotion is a core fundamental attribute of humans. Using music to induce emotional responses from subjects to better facilitate human behavior shaping have been effective across domains of health, education, and retail. Computationally model the musically-induced emotion provides necessary content-based analytics for large-scale and wide-applicability of such human-centered applications. In this work, we propose a relationship neural network architecture to learn to regress the induced emotion attributes with an auxiliary task of genre classification. Our proposed Genre-Affect Relationship Network with homoscedastic uncertainty weighting embeds the relationship between affect and genre as tensor normal prior within task-specific layers; the architecture is optimized further by incorporating task-specific uncertainty. The proposed architecture achieves a state-of-art 0.564 average Pearson correlation computed over nine induced emotion ratings in the Emotify database. Furthermore, we provide an analysis to understand the relationship between the induced emotions of these musical pieces and their associated genres.
Figures
A schematic ofour proposed Genre-Affect Relationship Network architecture
A schematic ofour proposed Genre-Affect Relationship Network architecture
Keywords
multi-task learning | induced emotion | music | homoscedastic uncertainty | relationship network
Authors
Publication Date
2018/07/23
Conference
IEEE International Conference on Multimedia and Expo (ICME)
2018 IEEE International Conference on Multimedia and Expo (ICME)
DOI
10.1109/icme.2018.8486570
Publisher
IEEE