{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sounding-video-generator-a-unified-framework","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","arxiv_id":"2303.16541","date":"2023-03-29","proceeding":null,"authors":["Jiawei Liu","Weining Wang","Sihan Chen","Xinxin Zhu","Jing Liu"],"abstract":"As a combination of visual and audio signals, video is inherently multi-modal. However, existing video generation methods are primarily intended for the synthesis of visual frames, whereas audio signals in realistic videos are disregarded. In this work, we concentrate on a rarely investigated problem of text guided sounding video generation and propose the Sounding Video Generator (SVG), a unified framework for generating realistic videos along with audio signals. Specifically, we present the SVG-VQGAN to transform visual frames and audio melspectrograms into discrete tokens. SVG-VQGAN applies a novel hybrid contrastive learning method to model inter-modal and intra-modal consistency and improve the quantized representations. A cross-modal attention module is employed to extract associated features of visual frames and audio signals for contrastive learning. Then, a Transformer-based decoder is used to model associations between texts, visual frames, and audio signals at token level for auto-regressive sounding video generation. AudioSetCap, a human annotated text-video-audio paired dataset, is produced for training SVG. Experimental results demonstrate the superiority of our method when compared with existing textto-video generation methods as well as audio generation methods on Kinetics and VAS datasets.","url_abs":"https://arxiv.org/abs/2303.16541v1","url_pdf":"https://arxiv.org/pdf/2303.16541v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sounding-video-generator-a-unified-framework","repo_url":"https://github.com/jwliu-cc/svg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}