{"paper":{"title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Christian Fuegen, Egor Lakomkin, Honglie Chen, J\\'achym Kol\\'a\\v{r}, Konstantinos Vougioukas, Maja Pantic, Morrie Doulaty, Niko Moritz, Pingchuan Ma, Ruiming Xie, Stavros Petridis, Xubo Liu","submitted_at":"2023-03-30T07:43:27Z","abstract_excerpt":"Recently reported state-of-the-art results in visual speech recognition (VSR) often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are limited in size. In this paper, for the first time, we study the potential of leveraging synthetic visual data for VSR. Our method, termed SynthVSR, substantially improves the performance of VSR systems with synthetic lip movements. The key idea behind SynthVSR is to leverage a speech-driven lip animation model that generates lip movements conditioned on the input speech. The speech-driven lip animation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17200","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.17200/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}