{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ROWYWVOFAVJNLUY65OYUA67TKB","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":"cf236d4546873753f1de89603f04bca5ff442384692a23e54d8c01f7b6bd39aa","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-03T02:45:06Z","title_canon_sha256":"726de980107cf57694023f17360588ef96604c82121e6af07c03afa5d08e4e18"},"schema_version":"1.0","source":{"id":"2008.00620","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.00620","created_at":"2026-07-05T03:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"2008.00620v2","created_at":"2026-07-05T03:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00620","created_at":"2026-07-05T03:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"ROWYWVOFAVJN","created_at":"2026-07-05T03:09:42Z"},{"alias_kind":"pith_short_16","alias_value":"ROWYWVOFAVJNLUY6","created_at":"2026-07-05T03:09:42Z"},{"alias_kind":"pith_short_8","alias_value":"ROWYWVOF","created_at":"2026-07-05T03:09:42Z"}],"graph_snapshots":[{"event_id":"sha256:6a8701d0c3e56b54baead6f017fd09df645b51d9ac01f97ce6a4853052b48a6d","target":"graph","created_at":"2026-07-05T03:09:42Z","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/2008.00620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiovisual speech synthesis is the problem of synthesizing a talking face while maximizing the coherency of the acoustic and visual speech. In this paper, we propose and compare two audiovisual speech synthesis systems for 3D face models. The first system is the AVTacotron2, which is an end-to-end text-to-audiovisual speech synthesizer based on the Tacotron2 architecture. AVTacotron2 converts a sequence of phonemes representing the sentence to synthesize into a sequence of acoustic features and the corresponding controllers of a face model. The output acoustic features are used to condition a","authors_text":"Ahmed Hussen Abdelaziz, Anushree Prasanna Kumar, Chloe Seivwright, Gabriele Fanelli, Justin Binder, Sachin Kajarekar, Yannis Stylianou","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-03T02:45:06Z","title":"Audiovisual Speech Synthesis using Tacotron2"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00620","kind":"arxiv","version":2},"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":"sha256:55918ce10cb61f73989a6222856adac6b32f269ecac5676317ab3ed94da28bb5","target":"record","created_at":"2026-07-05T03:09:42Z","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":"cf236d4546873753f1de89603f04bca5ff442384692a23e54d8c01f7b6bd39aa","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-03T02:45:06Z","title_canon_sha256":"726de980107cf57694023f17360588ef96604c82121e6af07c03afa5d08e4e18"},"schema_version":"1.0","source":{"id":"2008.00620","kind":"arxiv","version":2}},"canonical_sha256":"8bad8b55c50552d5d31eebb1407bf3504093f140bf2e1e2d94233bfb28f1639d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bad8b55c50552d5d31eebb1407bf3504093f140bf2e1e2d94233bfb28f1639d","first_computed_at":"2026-07-05T03:09:42.941159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:42.941159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HVjeIxqj3yXWI9dHXq6bi51cmBEpqYzo2f84R8+spqDc4GIABenuowbqCjbkKl5+xVyn9btllFkuSbR395B8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:42.941751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.00620","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55918ce10cb61f73989a6222856adac6b32f269ecac5676317ab3ed94da28bb5","sha256:6a8701d0c3e56b54baead6f017fd09df645b51d9ac01f97ce6a4853052b48a6d"],"state_sha256":"90c1a2ff75df134316eaccd3d68d7d3bba1e9b3d96d80593e415be439496e1c7"}