{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TULFDSS3IHCWRUJTNYDODYIWE2","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":"e42618f45fff93082aa6961533f8606ad1429bac22d9272be4cabf52adda1351","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T17:12:30Z","title_canon_sha256":"9a47186eb4f2a0f6ce9228a5d9d196a3d0ee34cd0fa65cef08445b642f27e364"},"schema_version":"1.0","source":{"id":"2104.13332","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.13332","created_at":"2026-07-05T04:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2104.13332v3","created_at":"2026-07-05T04:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13332","created_at":"2026-07-05T04:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"TULFDSS3IHCW","created_at":"2026-07-05T04:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"TULFDSS3IHCWRUJT","created_at":"2026-07-05T04:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"TULFDSS3","created_at":"2026-07-05T04:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:556bd5ea0f73c1cad2a91198d4f02870a24a3c8ee79e46a008570b47f281eed0","target":"graph","created_at":"2026-07-05T04:48:34Z","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/2104.13332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-speech is the process of reconstructing the audio speech from a video of a spoken utterance. Previous approaches to this task have relied on a two-step process where an intermediate representation is inferred from the video, and is then decoded into waveform audio using a vocoder or a waveform reconstruction algorithm. In this work, we propose a new end-to-end video-to-speech model based on Generative Adversarial Networks (GANs) which translates spoken video to waveform end-to-end without using any intermediate representation or separate waveform synthesis algorithm. Our model consist","authors_text":"Bj\\\"orn W. Schuller, Konstantinos Vougioukas, Maja Pantic, Pingchuan Ma, Rodrigo Mira, Stavros Petridis","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T17:12:30Z","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13332","kind":"arxiv","version":3},"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":"sha256:5ed0e36b742164e9b60c0b5798101b97a37372cb783414494312605f33393c85","target":"record","created_at":"2026-07-05T04:48:34Z","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":"e42618f45fff93082aa6961533f8606ad1429bac22d9272be4cabf52adda1351","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T17:12:30Z","title_canon_sha256":"9a47186eb4f2a0f6ce9228a5d9d196a3d0ee34cd0fa65cef08445b642f27e364"},"schema_version":"1.0","source":{"id":"2104.13332","kind":"arxiv","version":3}},"canonical_sha256":"9d1651ca5b41c568d1336e06e1e11626bdf7a72c653b03319fb845bfbade5536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d1651ca5b41c568d1336e06e1e11626bdf7a72c653b03319fb845bfbade5536","first_computed_at":"2026-07-05T04:48:34.003954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:48:34.003954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kHDDo1v3dLhitWil1qI7aISIdVGTCPPndnrIc1P9oqqkQLMYXPql+MFvZols2aenyOIUu4w+NHwCos5KerXwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:48:34.004437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.13332","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ed0e36b742164e9b60c0b5798101b97a37372cb783414494312605f33393c85","sha256:556bd5ea0f73c1cad2a91198d4f02870a24a3c8ee79e46a008570b47f281eed0"],"state_sha256":"2dcd32a258692f2f1ff3b701e911b9c4e169b2a797c749156ef504ed5696acea"}