Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
Tan, Weiting, Lian, Jiachen, Inaguma, Hirofumi, Tomasello, Paden, Koehn, Philipp, Ma, Xutai
–arXiv.org Artificial Intelligence
We present an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model. We explore multiple visual encoders and multimodal fusion strategies during pre-training to identify the most effective integration approach. Subsequent fine-tuning on emotion recognition and expressive dialogue tasks yields substantial gains over speech-only baselines (e.g., +5 F1 in emotion recognition). AVLM highlights the value of expressive visual information in guiding speech generation and offers a foundation for end-to-end multimodal conversational systems.
arXiv.org Artificial Intelligence
Aug-29-2025
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Information Technology > Security & Privacy (0.46)
- Technology: