{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TM2S4C4H7TZTXU7FYYO7GPJDE6","short_pith_number":"pith:TM2S4C4H","schema_version":"1.0","canonical_sha256":"9b352e0b87fcf33bd3e5c61df33d2327befa247d53364bf7f1c8cf258e0735e5","source":{"kind":"arxiv","id":"1905.03079","version":1},"attestation_state":"computed","paper":{"title":"Capture, Learning, and Synthesis of 3D Speaking Styles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Ranjan, Cassidy Laidlaw, Daniel Cudeiro, Michael J. Black, Timo Bolkart","submitted_at":"2019-05-08T14:16:37Z","abstract_excerpt":"Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input - even speech in languages other than English - and "},"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":"1905.03079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T14:16:37Z","cross_cats_sorted":[],"title_canon_sha256":"511f115e7a70c112a90aa353ddf61bb51b458c9a7756ba5266f312b3b8ec937e","abstract_canon_sha256":"343dceebe9e477d0a69bfcbe231ecd5fb24a0469a674385d4bbd292c73812c30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:42.934918Z","signature_b64":"je9iHKoqwlkpEfa8p/IRVjPMLn1kwUDRiGEccoVG8+VbJuN63lDzUubnZXPOR0kxgsGxy99RRWvm/Q2/3a4jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b352e0b87fcf33bd3e5c61df33d2327befa247d53364bf7f1c8cf258e0735e5","last_reissued_at":"2026-05-17T23:46:42.934438Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:42.934438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capture, Learning, and Synthesis of 3D Speaking Styles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Ranjan, Cassidy Laidlaw, Daniel Cudeiro, Michael J. Black, Timo Bolkart","submitted_at":"2019-05-08T14:16:37Z","abstract_excerpt":"Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input - even speech in languages other than English - and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03079","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":""},"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":"1905.03079","created_at":"2026-05-17T23:46:42.934512+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03079v1","created_at":"2026-05-17T23:46:42.934512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03079","created_at":"2026-05-17T23:46:42.934512+00:00"},{"alias_kind":"pith_short_12","alias_value":"TM2S4C4H7TZT","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TM2S4C4H7TZTXU7F","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TM2S4C4H","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6","json":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6.json","graph_json":"https://pith.science/api/pith-number/TM2S4C4H7TZTXU7FYYO7GPJDE6/graph.json","events_json":"https://pith.science/api/pith-number/TM2S4C4H7TZTXU7FYYO7GPJDE6/events.json","paper":"https://pith.science/paper/TM2S4C4H"},"agent_actions":{"view_html":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6","download_json":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6.json","view_paper":"https://pith.science/paper/TM2S4C4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03079&json=true","fetch_graph":"https://pith.science/api/pith-number/TM2S4C4H7TZTXU7FYYO7GPJDE6/graph.json","fetch_events":"https://pith.science/api/pith-number/TM2S4C4H7TZTXU7FYYO7GPJDE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6/action/storage_attestation","attest_author":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6/action/author_attestation","sign_citation":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6/action/citation_signature","submit_replication":"https://pith.science/pith/TM2S4C4H7TZTXU7FYYO7GPJDE6/action/replication_record"}},"created_at":"2026-05-17T23:46:42.934512+00:00","updated_at":"2026-05-17T23:46:42.934512+00:00"}