Search Results for author:
Found 2 papers, 0 papers with code
StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing
It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync.
Deep-learned speckle pattern and its application to ghost imaging
Our method, therefore, outperforms the other techniques for ghost imaging, particularly its ability to retrieve high-quality images with extremely low sampling ratios.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
