{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:D2D5SQWBJPT4D5C7Y6B4PQ3BDB","short_pith_number":"pith:D2D5SQWB","schema_version":"1.0","canonical_sha256":"1e87d942c14be7c1f45fc783c7c3611863d7cbf447f4cedfa945f990635f3dde","source":{"kind":"arxiv","id":"2004.02541","version":2},"attestation_state":"computed","paper":{"title":"Vocoder-Based Speech Synthesis from Silent Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.AS","authors_text":"Daniel Michelsanti, Emilia G\\'omez, Gloria Haro, Jesper Jensen, Olga Slizovskaia, Zheng-Hua Tan","submitted_at":"2020-04-06T10:22:04Z","abstract_excerpt":"Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility for untrained lip readers. In this paper, we present a way to synthesise speech from the silent video of a talker using deep learning. The system learns a mapping function from raw video frames to acoustic features and reconstructs the speech with a vocoder synthesis algorithm. To improve speech reconstruction performance, our model is also trained to predict text information in a multi-task learning fashion and it "},"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":"2004.02541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-04-06T10:22:04Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"978976cfffbcd53a8864eb57bef8278bc2a28c3b2b03ecaf4074c0f5b48b58de","abstract_canon_sha256":"33667398919648c8e47255e5ecd526cbde4269a729cdae60e3fce870dda59338"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:22.521886Z","signature_b64":"Qn3dlNBKrTYbIXPRTBlv6R7R61NCXrfPoeYVOBx8Eess6MWqWA+tm7GIUl4ZAGeBQt3Dh62F3V+IoeYYG7q3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e87d942c14be7c1f45fc783c7c3611863d7cbf447f4cedfa945f990635f3dde","last_reissued_at":"2026-07-05T01:27:22.521450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:22.521450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vocoder-Based Speech Synthesis from Silent Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.AS","authors_text":"Daniel Michelsanti, Emilia G\\'omez, Gloria Haro, Jesper Jensen, Olga Slizovskaia, Zheng-Hua Tan","submitted_at":"2020-04-06T10:22:04Z","abstract_excerpt":"Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility for untrained lip readers. In this paper, we present a way to synthesise speech from the silent video of a talker using deep learning. The system learns a mapping function from raw video frames to acoustic features and reconstructs the speech with a vocoder synthesis algorithm. To improve speech reconstruction performance, our model is also trained to predict text information in a multi-task learning fashion and it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02541","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/2004.02541/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":"2004.02541","created_at":"2026-07-05T01:27:22.521513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02541v2","created_at":"2026-07-05T01:27:22.521513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02541","created_at":"2026-07-05T01:27:22.521513+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2D5SQWBJPT4","created_at":"2026-07-05T01:27:22.521513+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2D5SQWBJPT4D5C7","created_at":"2026-07-05T01:27:22.521513+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2D5SQWB","created_at":"2026-07-05T01:27:22.521513+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/D2D5SQWBJPT4D5C7Y6B4PQ3BDB","json":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB.json","graph_json":"https://pith.science/api/pith-number/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/graph.json","events_json":"https://pith.science/api/pith-number/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/events.json","paper":"https://pith.science/paper/D2D5SQWB"},"agent_actions":{"view_html":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB","download_json":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB.json","view_paper":"https://pith.science/paper/D2D5SQWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02541&json=true","fetch_graph":"https://pith.science/api/pith-number/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/graph.json","fetch_events":"https://pith.science/api/pith-number/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/action/storage_attestation","attest_author":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/action/author_attestation","sign_citation":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/action/citation_signature","submit_replication":"https://pith.science/pith/D2D5SQWBJPT4D5C7Y6B4PQ3BDB/action/replication_record"}},"created_at":"2026-07-05T01:27:22.521513+00:00","updated_at":"2026-07-05T01:27:22.521513+00:00"}