{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6DAOSITGZTMVT7ZQHXBJYIDHAL","short_pith_number":"pith:6DAOSITG","schema_version":"1.0","canonical_sha256":"f0c0e92266ccd959ff303dc29c206702e5beda349e79c96a6d6f8ea31850414a","source":{"kind":"arxiv","id":"2301.06059","version":1},"attestation_state":"computed","paper":{"title":"Learning Audio-Driven Viseme Dynamics for 3D Face Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Changhai Chen, Di Kang, Haoxian Zhang, Linchao Bao, Tangli Xue, Xuefei Zhe, Yue Qian","submitted_at":"2023-01-15T09:55:46Z","abstract_excerpt":"We present a novel audio-driven facial animation approach that can generate realistic lip-synchronized 3D facial animations from the input audio. Our approach learns viseme dynamics from speech videos, produces animator-friendly viseme curves, and supports multilingual speech inputs. The core of our approach is a novel parametric viseme fitting algorithm that utilizes phoneme priors to extract viseme parameters from speech videos. With the guidance of phonemes, the extracted viseme curves can better correlate with phonemes, thus more controllable and friendly to animators. To support multiling"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.06059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2023-01-15T09:55:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8a66df6e853734c26aee04c6bece335361fe5557e643dacc577f015ad4bcc49b","abstract_canon_sha256":"0ac3b41b316531ee5be51aede71b9792b24b98a8d1177822887470af4e79b936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:27.517079Z","signature_b64":"Xw52xxGQ+koec/oGc5xD3fcgbcckcTsqf5Z/+BdJkQRN+URhFA5qP+o5krLzkDX4yGwa/yauNzTxFbBq1xSpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0c0e92266ccd959ff303dc29c206702e5beda349e79c96a6d6f8ea31850414a","last_reissued_at":"2026-07-05T05:33:27.516604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:27.516604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Audio-Driven Viseme Dynamics for 3D Face Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Changhai Chen, Di Kang, Haoxian Zhang, Linchao Bao, Tangli Xue, Xuefei Zhe, Yue Qian","submitted_at":"2023-01-15T09:55:46Z","abstract_excerpt":"We present a novel audio-driven facial animation approach that can generate realistic lip-synchronized 3D facial animations from the input audio. Our approach learns viseme dynamics from speech videos, produces animator-friendly viseme curves, and supports multilingual speech inputs. The core of our approach is a novel parametric viseme fitting algorithm that utilizes phoneme priors to extract viseme parameters from speech videos. With the guidance of phonemes, the extracted viseme curves can better correlate with phonemes, thus more controllable and friendly to animators. To support multiling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06059","kind":"arxiv","version":1},"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/2301.06059/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.06059","created_at":"2026-07-05T05:33:27.516678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06059v1","created_at":"2026-07-05T05:33:27.516678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06059","created_at":"2026-07-05T05:33:27.516678+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DAOSITGZTMV","created_at":"2026-07-05T05:33:27.516678+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DAOSITGZTMVT7ZQ","created_at":"2026-07-05T05:33:27.516678+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DAOSITG","created_at":"2026-07-05T05:33:27.516678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07478","citing_title":"AudioFace: Language-Assisted Speech-Driven Facial Animation with Multimodal Language Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL","json":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL.json","graph_json":"https://pith.science/api/pith-number/6DAOSITGZTMVT7ZQHXBJYIDHAL/graph.json","events_json":"https://pith.science/api/pith-number/6DAOSITGZTMVT7ZQHXBJYIDHAL/events.json","paper":"https://pith.science/paper/6DAOSITG"},"agent_actions":{"view_html":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL","download_json":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL.json","view_paper":"https://pith.science/paper/6DAOSITG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06059&json=true","fetch_graph":"https://pith.science/api/pith-number/6DAOSITGZTMVT7ZQHXBJYIDHAL/graph.json","fetch_events":"https://pith.science/api/pith-number/6DAOSITGZTMVT7ZQHXBJYIDHAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL/action/storage_attestation","attest_author":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL/action/author_attestation","sign_citation":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL/action/citation_signature","submit_replication":"https://pith.science/pith/6DAOSITGZTMVT7ZQHXBJYIDHAL/action/replication_record"}},"created_at":"2026-07-05T05:33:27.516678+00:00","updated_at":"2026-07-05T05:33:27.516678+00:00"}