DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 10671-10680
Abstract
No abstract availableAll Related Versions
This publication has 14 references indexed in Scilit:
- CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation2024
- Anim-400K: A Large-Scale Dataset for Automated End to End Dubbing of Video2024
- CLAP Learning Audio Concepts from Natural Language Supervision2023
- Learning to Dub Movies via Hierarchical Prosody Models2023
- ImageBind One Embedding Space to Bind Them All2023
- Conditional Generation of Audio from Video via Foley Analogies2023
- V2C: Visual Voice Cloning2022
- More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech2022
- PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Vggsound: A Large-Scale Audio-Visual Dataset2020