TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation
This work addresses the problem of improving emotion recognition accuracy for dialogue systems, though it appears incremental as it builds on existing multimodal fusion techniques.
The paper tackles the challenge of weak non-verbal modalities in multimodal emotion recognition in conversation by proposing TelME, a teacher-leading fusion network that uses cross-modal knowledge distillation from a language model to enhance weak modalities, achieving state-of-the-art performance on the MELD dataset.
Emotion Recognition in Conversation (ERC) plays a crucial role in enabling dialogue systems to effectively respond to user requests. The emotions in a conversation can be identified by the representations from various modalities, such as audio, visual, and text. However, due to the weak contribution of non-verbal modalities to recognize emotions, multimodal ERC has always been considered a challenging task. In this paper, we propose Teacher-leading Multimodal fusion network for ERC (TelME). TelME incorporates cross-modal knowledge distillation to transfer information from a language model acting as the teacher to the non-verbal students, thereby optimizing the efficacy of the weak modalities. We then combine multimodal features using a shifting fusion approach in which student networks support the teacher. TelME achieves state-of-the-art performance in MELD, a multi-speaker conversation dataset for ERC. Finally, we demonstrate the effectiveness of our components through additional experiments.