Tapir Lab’s Lip-Sync Method is the implementation of a language-independent lip-sync method that is based on extended linear predictive coding. The proposed method operates on the recording of acoustic signals which are acquired by a standard single-channel off–the–shelf microphone and exploits the statistical characteristics of acoustic signals produced by human speech. Mathematical background and detailed description of the method can be found on the paper. Information about the paper can be found on Publications page.
Git repository of Tapir Lab.’s Lip-Sync Method: https://github.com/TapirLab/lip-sync