{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UAW6EHTQWL6V3EAOMQ46RLSEH4","short_pith_number":"pith:UAW6EHTQ","schema_version":"1.0","canonical_sha256":"a02de21e70b2fd5d900e6439e8ae443f04fed7e2bbf8be8bd24cd75d45e650ba","source":{"kind":"arxiv","id":"1710.00920","version":2},"attestation_state":"computed","paper":{"title":"End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai X. Pham, Vladimir Pavlovic, Yuting Wang","submitted_at":"2017-10-02T21:44:32Z","abstract_excerpt":"We present a deep learning framework for real-time speech-driven 3D facial animation from just raw waveforms. Our deep neural network directly maps an input sequence of speech audio to a series of micro facial action unit activations and head rotations to drive a 3D blendshape face model. In particular, our deep model is able to learn the latent representations of time-varying contextual information and affective states within the speech. Hence, our model not only activates appropriate facial action units at inference to depict different utterance generating actions, in the form of lip movemen"},"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":"1710.00920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-02T21:44:32Z","cross_cats_sorted":[],"title_canon_sha256":"7aedc138f315754d4c260594ce77f5ec5b6e46ab9ef66439bb9115026db2051d","abstract_canon_sha256":"4798920d1aa074d1ebab138f12c672b8df33c883ef83fb4e7a3a62423a77c919"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:29.605552Z","signature_b64":"UKhjy1QNhaWgpp02spkwsHKCAhmDjplD0IfC5fg99kTKrOxI3aVmhxkxoLOihI7SwR+HNVHLVvww//XlWAtxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a02de21e70b2fd5d900e6439e8ae443f04fed7e2bbf8be8bd24cd75d45e650ba","last_reissued_at":"2026-05-18T00:28:29.604815Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:29.604815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai X. Pham, Vladimir Pavlovic, Yuting Wang","submitted_at":"2017-10-02T21:44:32Z","abstract_excerpt":"We present a deep learning framework for real-time speech-driven 3D facial animation from just raw waveforms. Our deep neural network directly maps an input sequence of speech audio to a series of micro facial action unit activations and head rotations to drive a 3D blendshape face model. In particular, our deep model is able to learn the latent representations of time-varying contextual information and affective states within the speech. Hence, our model not only activates appropriate facial action units at inference to depict different utterance generating actions, in the form of lip movemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00920","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":""},"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":"1710.00920","created_at":"2026-05-18T00:28:29.604990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.00920v2","created_at":"2026-05-18T00:28:29.604990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00920","created_at":"2026-05-18T00:28:29.604990+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAW6EHTQWL6V","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAW6EHTQWL6V3EAO","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAW6EHTQ","created_at":"2026-05-18T12:31:46.661854+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/UAW6EHTQWL6V3EAOMQ46RLSEH4","json":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4.json","graph_json":"https://pith.science/api/pith-number/UAW6EHTQWL6V3EAOMQ46RLSEH4/graph.json","events_json":"https://pith.science/api/pith-number/UAW6EHTQWL6V3EAOMQ46RLSEH4/events.json","paper":"https://pith.science/paper/UAW6EHTQ"},"agent_actions":{"view_html":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4","download_json":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4.json","view_paper":"https://pith.science/paper/UAW6EHTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.00920&json=true","fetch_graph":"https://pith.science/api/pith-number/UAW6EHTQWL6V3EAOMQ46RLSEH4/graph.json","fetch_events":"https://pith.science/api/pith-number/UAW6EHTQWL6V3EAOMQ46RLSEH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4/action/storage_attestation","attest_author":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4/action/author_attestation","sign_citation":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4/action/citation_signature","submit_replication":"https://pith.science/pith/UAW6EHTQWL6V3EAOMQ46RLSEH4/action/replication_record"}},"created_at":"2026-05-18T00:28:29.604990+00:00","updated_at":"2026-05-18T00:28:29.604990+00:00"}