{"paper":{"title":"Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jun Saito, Taku Komura, Wenping Wang, Yingruo Fan, Zhaojiang Lin","submitted_at":"2021-12-04T01:37:22Z","abstract_excerpt":"Speech-driven 3D facial animation with accurate lip synchronization has been widely studied. However, synthesizing realistic motions for the entire face during speech has rarely been explored. In this work, we present a joint audio-text model to capture the contextual information for expressive speech-driven 3D facial animation. The existing datasets are collected to cover as many different phonemes as possible instead of sentences, thus limiting the capability of the audio-based model to learn more diverse contexts. To address this, we propose to leverage the contextual text embeddings extrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02214","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/2112.02214/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"}