Bridging Text and Speech for Emotion Understanding: An Explainable Multimodal Transformer Fusion Framework with Unified Audio–Text Attribution
Year: 2025
Type: article
Abstract: Conversational interactions, rich in both linguistic and vocal cues, provide a natural context for studying these processes. In this work, we propose an explainable multimodal transformer framework that integrates textual semantics (via RoBERTa) and acoustic prosody (via WavLM) to advance emotion understanding. By projecting both modalities into a shared latent space, our model captures the complementary contributions of language and speech to affective communication, achieving an 0.83 accuracy value across five emotion categories. Crucially, we embed explainable AI (XAI) techniques including Integrated Gradients and Occlusion to attribute predictions to specific linguistic tokens and prosodic patterns, thereby aligning computational mechanisms with human cognitive processes of emotion perception. Beyond performance gains, this work demonstrates how multimodal AI systems can support transparent, human-centered emotion recognition.
Source: Journal of Intelligence
Authors: Ashutosh Pandey, Jasmeet Singh, Maninder Kaur
Institution: Thapar Institute of Engineering & Technology
Language: English
Topic: Emotion and Mood Recognition
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $3,137
OpenAlex ID: W4416944656