Summary of Telme: Teacher-leading Multimodal Fusion Network For Emotion Recognition in Conversation, by Taeyang Yun et al.
TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation
by Taeyang Yun, Hyunkuk Lim, Jeonghwan Lee, Min Song
First submitted to arxiv on: 16 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Teacher-leading Multimodal fusion network for Emotion Recognition in Conversation (TelME) enables dialogue systems to effectively respond to user requests by incorporating cross-modal knowledge distillation and shifting fusion approaches. TelME optimizes the efficacy of weak modalities, such as non-verbal cues, and achieves state-of-the-art performance on MELD, a multi-speaker conversation dataset for ERC. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way for computers to understand emotions in conversations. It’s like teaching students how to recognize emotions from different sources, like what someone says or how they look. The approach is called TelME and it uses a special kind of learning that helps weak signals get stronger. This makes the computer better at understanding emotions. In tests on a big dataset, TelME did really well. |
Keywords
* Artificial intelligence * Knowledge distillation
