Playing For You: Text Prompt-guided Joint Audio-visual Generation for Narrating Faces using Multi-entangled Latent Space

27 Sept 2024 (modified: 05 Feb 2025)Submitted to ICLR 2025EveryoneRevisionsBibTeXCC BY 4.0
Keywords: Generating Multimoda
Abstract:

We present a novel approach for generating realistic speaking and taking faces by synthesizing a person’s voice and facial movements from a static image, a voice profile, and a target text. The model encodes the prompt/driving text, a driving image and the voice profile of an individual and then combines them to pass it to the multi-entangled latent space to foster key-vale and query for audio and video modality generation pipeline. The multi-entangled latent space is responsible for establishing the spatiotemporal person-specific features between the modalities. Further, entangled features are passed to the respective decoder of each modality for output audio and video generation. Our experiments and analysis through standard metrics showcase the effectiveness of our model. All model checkpoints, code and the proposed dataset can be found at: https://github.com/Playing-for-you.

Supplementary Material: pdf
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10887
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview