There are 2 repositories under lip topic.
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
LUKSO Improvement Proposals. Repository for the LUKSO Blockchain Improvement Proposals (LIPs) and LUKSO Standards Process (LSP).
Learning Lip Sync of Obama from Speech Audio
Trained deep neural-net models for estimating articulatory keypoints from midsagittal ultrasound tongue videos and front-view lip camera videos using DeepLabCut. This research is by Wrench, A. and Balch-Tomes, J. (2022) (https://www.mdpi.com/1424-8220/22/3/1133) (https://doi.org/10.3390/s22031133).
JPPNet implementation in TensorFlow for human parsing
The Loki Improvement Proposal repository
A simple Unity C# script that will drive a lower jaw based on audio amplitude from an audio clip. It uses a low pass filter to smooth the output. A custom SLATE action is included called "PlayAudioWithLipSync" use it in Slate to drive the jaw in your cutscenes.
Rust library which implements reading resources used in Fallout™.
Student to Site Allocation with Integer Linear Programming
ANSI C library which implements reading resources used in Fallout™.