@inproceedings{inproceedings, title = {{VisualSpeech: Enhancing Prosody Modeling in TTS Using Video}}, publisher = {{International Speech Communication Association (ISCA)}}, url = {{https://eprints.whiterose.ac.uk/id/eprint/232120 https://www.isca-archive.org/interspeech_2025/que25_interspeech.html }}, year = {{2025}}, month = {{8}}, author = {{Que S and Ragni A}}, doi = {{10.21437/Interspeech.2025-1494}}, journal = {{Proceedings of Interspeech 2025}}, pages = {{3778-3782}}, note = {{Accessed on 2025/11/23}}}