A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild

23 Aug 2020  ·  K R Prajwal, Rudrabha Mukhopadhyay, Vinay Namboodiri, C. V. Jawahar ·

In this work, we investigate the problem of lip-syncing a talking face video of an arbitrary identity to match a target speech segment. Current works excel at producing accurate lip movements on a static image or videos of specific people seen during the training phase... However, they fail to accurately morph the lip movements of arbitrary identities in dynamic, unconstrained talking face videos, resulting in significant parts of the video being out-of-sync with the new audio. We identify key reasons pertaining to this and hence resolve them by learning from a powerful lip-sync discriminator. Next, we propose new, rigorous evaluation benchmarks and metrics to accurately measure lip synchronization in unconstrained videos. Extensive quantitative evaluations on our challenging benchmarks show that the lip-sync accuracy of the videos generated by our Wav2Lip model is almost as good as real synced videos. We provide a demo video clearly showing the substantial impact of our Wav2Lip model and evaluation benchmarks on our website: \url{cvit.iiit.ac.in/research/projects/cvit-projects/a-lip-sync-expert-is-all-you-need-for-speech-to-lip-generation-in-the-wild}. The code and models are released at this GitHub repository: \url{github.com/Rudrabha/Wav2Lip}. You can also try out the interactive demo at this link: \url{bhaasha.iiit.ac.in/lipsync}. read more

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Unconstrained Lip-synchronization LRS2 Wav2Lip LSE-D 6.386 # 2
LSE-C 7.781 # 1
FID 4.887 # 2
Unconstrained Lip-synchronization LRS2 Wav2Lip + GAN LSE-D 6.469 # 1
FID 4.446 # 1
Unconstrained Lip-synchronization LRS3 Wav2Lip LSE-D 6.652 # 2
LSE-C 7.887 # 1
FID 4.844 # 2
Unconstrained Lip-synchronization LRS3 Wav2Lip + GAN LSE-D 6.986 # 1
LSE-C 7.574 # 2
FID 4.35 # 1
Unconstrained Lip-synchronization LRW Wav2Lip LSE-D 6.512 # 2
LSE-C 7.49 # 1
FID 3.189 # 2
Unconstrained Lip-synchronization LRW Wav2Lip + GAN LSE-D 6.774 # 1
LSE-C 7.263 # 2
FID 2.475 # 1

Methods


No methods listed for this paper. Add relevant methods here