Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation

August 22, 2025 ยท Declared Dead ยท ๐Ÿ› EMNLP 2025

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Weiting Tan, Jiachen Lian, Hirofumi Inaguma, Paden Tomasello, Philipp Koehn, Xutai Ma arXiv ID 2508.16188 Category cs.CL: Computation & Language Cross-listed cs.CV, cs.MM, cs.SD, eess.AS Citations 0 Venue EMNLP 2025 Last Checked 6 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 9 years ago

Died the same way โ€” ๐Ÿ‘ป Ghosted