{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TULFDSS3IHCWRUJTNYDODYIWE2","short_pith_number":"pith:TULFDSS3","schema_version":"1.0","canonical_sha256":"9d1651ca5b41c568d1336e06e1e11626bdf7a72c653b03319fb845bfbade5536","source":{"kind":"arxiv","id":"2104.13332","version":3},"attestation_state":"computed","paper":{"title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Bj\\\"orn W. Schuller, Konstantinos Vougioukas, Maja Pantic, Pingchuan Ma, Rodrigo Mira, Stavros Petridis","submitted_at":"2021-04-27T17:12:30Z","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"},"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":"2104.13332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T17:12:30Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"9a47186eb4f2a0f6ce9228a5d9d196a3d0ee34cd0fa65cef08445b642f27e364","abstract_canon_sha256":"e42618f45fff93082aa6961533f8606ad1429bac22d9272be4cabf52adda1351"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:34.004437Z","signature_b64":"kHDDo1v3dLhitWil1qI7aISIdVGTCPPndnrIc1P9oqqkQLMYXPql+MFvZols2aenyOIUu4w+NHwCos5KerXwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d1651ca5b41c568d1336e06e1e11626bdf7a72c653b03319fb845bfbade5536","last_reissued_at":"2026-07-05T04:48:34.003954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:34.003954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Bj\\\"orn W. Schuller, Konstantinos Vougioukas, Maja Pantic, Pingchuan Ma, Rodrigo Mira, Stavros Petridis","submitted_at":"2021-04-27T17:12:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13332","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.13332/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2104.13332","created_at":"2026-07-05T04:48:34.004016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13332v3","created_at":"2026-07-05T04:48:34.004016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13332","created_at":"2026-07-05T04:48:34.004016+00:00"},{"alias_kind":"pith_short_12","alias_value":"TULFDSS3IHCW","created_at":"2026-07-05T04:48:34.004016+00:00"},{"alias_kind":"pith_short_16","alias_value":"TULFDSS3IHCWRUJT","created_at":"2026-07-05T04:48:34.004016+00:00"},{"alias_kind":"pith_short_8","alias_value":"TULFDSS3","created_at":"2026-07-05T04:48:34.004016+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/TULFDSS3IHCWRUJTNYDODYIWE2","json":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2.json","graph_json":"https://pith.science/api/pith-number/TULFDSS3IHCWRUJTNYDODYIWE2/graph.json","events_json":"https://pith.science/api/pith-number/TULFDSS3IHCWRUJTNYDODYIWE2/events.json","paper":"https://pith.science/paper/TULFDSS3"},"agent_actions":{"view_html":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2","download_json":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2.json","view_paper":"https://pith.science/paper/TULFDSS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13332&json=true","fetch_graph":"https://pith.science/api/pith-number/TULFDSS3IHCWRUJTNYDODYIWE2/graph.json","fetch_events":"https://pith.science/api/pith-number/TULFDSS3IHCWRUJTNYDODYIWE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2/action/storage_attestation","attest_author":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2/action/author_attestation","sign_citation":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2/action/citation_signature","submit_replication":"https://pith.science/pith/TULFDSS3IHCWRUJTNYDODYIWE2/action/replication_record"}},"created_at":"2026-07-05T04:48:34.004016+00:00","updated_at":"2026-07-05T04:48:34.004016+00:00"}