R
Rudrabha Mukhopadhyay
Researcher at International Institute of Information Technology, Hyderabad
Publications - 22
Citations - 593
Rudrabha Mukhopadhyay is an academic researcher from International Institute of Information Technology, Hyderabad. The author has contributed to research in topics: Computer science & Vocabulary. The author has an hindex of 5, co-authored 16 publications receiving 133 citations. Previous affiliations of Rudrabha Mukhopadhyay include Council of Scientific and Industrial Research & Heritage Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild
TL;DR: This work investigates the problem of lip-syncing a talking face video of an arbitrary identity to match a target speech segment, and identifies key reasons pertaining to this and hence resolves them by learning from a powerful lip-sync discriminator.
Proceedings ArticleDOI
A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild
TL;DR: Wav2Lip as mentioned in this paper proposes a powerful lip-sync discriminator to resolve the problem of significant parts of the video being out-of-sync with the new audio.
Proceedings ArticleDOI
Towards Automatic Face-to-Face Translation
Prajwal K R,Rudrabha Mukhopadhyay,Jerin Philip,Abhishek Kumar Jha,Vinay P. Namboodiri,C. V. Jawahar +5 more
TL;DR: LipGAN as discussed by the authors generates realistic talking faces from the translated audio, which can significantly improve the overall user experience for consuming and interacting with multimodal content across languages. But it is not suitable for the task of face-to-face translation.
Proceedings ArticleDOI
2D-3D CNN Based Architectures for Spectral Reconstruction from RGB Images
Sriharsha Koundinya,Himanshu Sharma,Manoj Sharma,Avinash Upadhyay,Raunak Manekar,Rudrabha Mukhopadhyay,Abhijit Karmakar,Santanu Chaudhury +7 more
TL;DR: This work proposes a 2D convolution neural network and a 3D convolved neural network based approaches for hyperspectral image reconstruction from RGB images that achieves very good performance in terms of MRAE and RMSE.
Proceedings ArticleDOI
Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
TL;DR: This work proposes a novel approach with key design choices to achieve accurate, natural lip to speech synthesis in such unconstrained scenarios for the first time and shows that its method is four times more intelligible than previous works in this space.