Emotional Cues Extraction and Fusion for Multi-modal Emotion Prediction and Recognition in Conversation

TL;DR

This paper introduces a novel multi-modal emotion prediction and recognition method that extracts fine-grained word-level cues and effectively fuses different modalities, improving performance on dialogue emotion tasks.

Contribution

It proposes a two-stage network for modality-specific emotion embedding and multi-modal feature fusion, addressing limitations of previous approaches in emotion cue extraction and modality integration.

Findings

Achieved superior results on IEMOCAP and MELD datasets.

Effectively captures fine-grained emotion cues at word level.

Improves multi-modal emotion prediction and recognition accuracy.

Abstract

Emotion Prediction in Conversation (EPC) aims to forecast the emotions of forthcoming utterances by utilizing preceding dialogues. Previous EPC approaches relied on simple context modeling for emotion extraction, overlooking fine-grained emotion cues at the word level. Additionally, prior works failed to account for the intrinsic differences between modalities, resulting in redundant information. To overcome these limitations, we propose an emotional cues extraction and fusion network, which consists of two stages: a modality-specific learning stage that utilizes word-level labels and prosody learning to construct emotion embedding spaces for each modality, and a two-step fusion stage for integrating multi-modal features. Moreover, the emotion features extracted by our model are also applicable to the Emotion Recognition in Conversation (ERC) task. Experimental results validate the efficacy of the proposed method, demonstrating superior performance on both IEMOCAP and MELD datasets.