{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G2DYIAIYVQ2EFH6RETFGTPTXVF","short_pith_number":"pith:G2DYIAIY","schema_version":"1.0","canonical_sha256":"3687840118ac34429fd124ca69be77a9692c7a87501596215e049724a35c5258","source":{"kind":"arxiv","id":"2205.02058","version":2},"attestation_state":"computed","paper":{"title":"SVTS: Scalable Video-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexandros Haliassos, Bj\\\"orn W. Schuller, Maja Pantic, Rodrigo Mira, Stavros Petridis","submitted_at":"2022-05-04T13:34:07Z","abstract_excerpt":"Video-to-speech synthesis (also known as lip-to-speech) refers to the translation of silent lip movements into the corresponding audio. This task has received an increasing amount of attention due to its self-supervised nature (i.e., can be trained without manual labelling) combined with the ever-growing collection of audio-visual data available online. Despite these strong motivations, contemporary video-to-speech works focus mainly on small- to medium-sized corpora with substantial constraints in both vocabulary and setting. In this work, we introduce a scalable video-to-speech framework con"},"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":"2205.02058","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-04T13:34:07Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"0e1088fa472a5f196413c9c21a2c0eec8c3b3c29c99e16fac143cc1cbc8e111e","abstract_canon_sha256":"cfb06da3f20917d3e41b4a1c110359b759a89e933ee4c6389a829ef47c34132a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:50.340738Z","signature_b64":"UDIotL5ILcGRAXBTc7/j690d52gFaOoe7wZRNXd5xKpThRjhc4ZklGBND3YBGP8Eeivw1hQqjcVJThMOrZV3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3687840118ac34429fd124ca69be77a9692c7a87501596215e049724a35c5258","last_reissued_at":"2026-07-05T04:48:50.340333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:50.340333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVTS: Scalable Video-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexandros Haliassos, Bj\\\"orn W. Schuller, Maja Pantic, Rodrigo Mira, Stavros Petridis","submitted_at":"2022-05-04T13:34:07Z","abstract_excerpt":"Video-to-speech synthesis (also known as lip-to-speech) refers to the translation of silent lip movements into the corresponding audio. This task has received an increasing amount of attention due to its self-supervised nature (i.e., can be trained without manual labelling) combined with the ever-growing collection of audio-visual data available online. Despite these strong motivations, contemporary video-to-speech works focus mainly on small- to medium-sized corpora with substantial constraints in both vocabulary and setting. In this work, we introduce a scalable video-to-speech framework con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02058","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.02058/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":"2205.02058","created_at":"2026-07-05T04:48:50.340392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02058v2","created_at":"2026-07-05T04:48:50.340392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02058","created_at":"2026-07-05T04:48:50.340392+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2DYIAIYVQ2E","created_at":"2026-07-05T04:48:50.340392+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2DYIAIYVQ2EFH6R","created_at":"2026-07-05T04:48:50.340392+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2DYIAIY","created_at":"2026-07-05T04:48:50.340392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.17690","citing_title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF","json":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF.json","graph_json":"https://pith.science/api/pith-number/G2DYIAIYVQ2EFH6RETFGTPTXVF/graph.json","events_json":"https://pith.science/api/pith-number/G2DYIAIYVQ2EFH6RETFGTPTXVF/events.json","paper":"https://pith.science/paper/G2DYIAIY"},"agent_actions":{"view_html":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF","download_json":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF.json","view_paper":"https://pith.science/paper/G2DYIAIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02058&json=true","fetch_graph":"https://pith.science/api/pith-number/G2DYIAIYVQ2EFH6RETFGTPTXVF/graph.json","fetch_events":"https://pith.science/api/pith-number/G2DYIAIYVQ2EFH6RETFGTPTXVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF/action/storage_attestation","attest_author":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF/action/author_attestation","sign_citation":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF/action/citation_signature","submit_replication":"https://pith.science/pith/G2DYIAIYVQ2EFH6RETFGTPTXVF/action/replication_record"}},"created_at":"2026-07-05T04:48:50.340392+00:00","updated_at":"2026-07-05T04:48:50.340392+00:00"}