EmotionBox: a music-element-driven emotional music generation system using Recurrent Neural Network
This addresses the need for emotional music generation in artistic expression, but it is incremental as it builds on existing music composition techniques with a focus on emotion control.
The paper tackles the problem of generating emotional music without requiring emotion-labeled datasets by using pitch histogram and note density as features to control emotions, and shows through subjective tests that their EmotionBox system performs competitively and balanced in arousing specified emotions compared to emotion-label-based methods.
With the development of deep neural networks, automatic music composition has made great progress. Although emotional music can evoke listeners' different emotions and it is important for artistic expression, only few researches have focused on generating emotional music. This paper presents EmotionBox -an music-element-driven emotional music generator that is capable of composing music given a specific emotion, where this model does not require a music dataset labeled with emotions. Instead, pitch histogram and note density are extracted as features that represent mode and tempo respectively to control music emotions. The subjective listening tests show that the Emotionbox has a more competitive and balanced performance in arousing a specified emotion than the emotion-label-based method.