{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2WGYCJ5TUD2NZCRF7JWCNMZFTT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9af3e077b007918d266414e03eb50e6f7ddab8c5d186fa96f0af2ef3361abf4e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T19:30:14Z","title_canon_sha256":"6780a53cfbfb6f2c496df8ecd56941a8d7bb698ba7d76a80d84e81d7f00c649c"},"schema_version":"1.0","source":{"id":"2007.09198","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09198","created_at":"2026-07-05T01:41:32Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09198v5","created_at":"2026-07-05T01:41:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09198","created_at":"2026-07-05T01:41:32Z"},{"alias_kind":"pith_short_12","alias_value":"2WGYCJ5TUD2N","created_at":"2026-07-05T01:41:32Z"},{"alias_kind":"pith_short_16","alias_value":"2WGYCJ5TUD2NZCRF","created_at":"2026-07-05T01:41:32Z"},{"alias_kind":"pith_short_8","alias_value":"2WGYCJ5T","created_at":"2026-07-05T01:41:32Z"}],"graph_snapshots":[{"event_id":"sha256:d3f44872e25afc447e255b4e124897f81f5cd91e521925864caca87dff70ca56","target":"graph","created_at":"2026-07-05T01:41:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.09198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person, where the output video has synchronized, realistic, and expressive rich body dynamics. We achieve this by first generating 3D skeleton movements from the audio sequence using a recurrent neural network (RNN), and then synthesizing the output video via a conditional generative adversarial network (GAN). To make the skeleton movement realistic and expressive, we embed the knowledge of an articulated 3D human skeleton and a learned dictionary of personal speech iconic","authors_text":"Hao Zhu, Miao Liao, Peng Wang, Ruigang Yang, Sibo Zhang, Xinxin Zuo","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T19:30:14Z","title":"Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09198","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b2d1184c88414f841ec07f3161f51ab811db8e544d0b0570c1ef15a777d41ae","target":"record","created_at":"2026-07-05T01:41:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9af3e077b007918d266414e03eb50e6f7ddab8c5d186fa96f0af2ef3361abf4e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T19:30:14Z","title_canon_sha256":"6780a53cfbfb6f2c496df8ecd56941a8d7bb698ba7d76a80d84e81d7f00c649c"},"schema_version":"1.0","source":{"id":"2007.09198","kind":"arxiv","version":5}},"canonical_sha256":"d58d8127b3a0f4dc8a25fa6c26b3259cddf35b75c070531c043bc66f7a7a206e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d58d8127b3a0f4dc8a25fa6c26b3259cddf35b75c070531c043bc66f7a7a206e","first_computed_at":"2026-07-05T01:41:32.737539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:32.737539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOjdGru7YRB0hWgGKzK8z7tUAxX7Ylp/arE2AK1ZYJSCQJeV7xlSJIaNlZTUgbJLbp1CxcjWgz3fzaE/tdN/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:32.737993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.09198","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b2d1184c88414f841ec07f3161f51ab811db8e544d0b0570c1ef15a777d41ae","sha256:d3f44872e25afc447e255b4e124897f81f5cd91e521925864caca87dff70ca56"],"state_sha256":"33c140704e6747d6cbf03b0a2df150b9da8d2a79b004b8bffd0cac05d3b28baa"}