@article{wav2lip2020,
  title = {Wav2Lip: A Lip Sync Expert Is All You Need},
  author = {Prajwal, K. R. and Mukhopadhyay, R. and Namboodiri, V. P. and Jawahar, C. V.},
  year = {2020},
  journal = {ACM Multimedia 2020},
  url = {https://arxiv.org/abs/2008.10010},
  abstract = {Prajwal, Mukhopadhyay, Namboodiri and Jawahar (2020) introduced Wav2Lip, an audio-driven lip-synchronisation method that uses a pretrained lip-sync expert discriminator as a teacher to train a generator producing accurate mouth movements for any speaker given an audio track. The key insight is using a discriminator specifically trained to judge lip-sync quality rather than general visual realism, producing accurate synchronisation on in-the-wild video without per-subject fine-tuning. Wav2Lip is speaker-agnostic and directly applicable to dubbing and dialogue-replacement workflows in animation and localisation. It became the open-source baseline cited by all subsequent talking-face and audio-driven animation research.},
  keywords = {voice-and-performance, character-animation},
  note = {AI \& Animation Education Knowledge Base}
}