{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KH677XNWNZZIO5FYSV66MKCWZP","short_pith_number":"pith:KH677XNW","schema_version":"1.0","canonical_sha256":"51fdffddb66e728774b8957de62856cbfb19c02a7fe3ea3b04ff653968761a0a","source":{"kind":"arxiv","id":"2305.19603","version":1},"attestation_state":"computed","paper":{"title":"Intelligible Lip-to-Speech Synthesis with Speech Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jeongsoo Choi, Minsu Kim, Yong Man Ro","submitted_at":"2023-05-31T07:17:32Z","abstract_excerpt":"In this paper, we propose a novel Lip-to-Speech synthesis (L2S) framework, for synthesizing intelligible speech from a silent lip movement video. Specifically, to complement the insufficient supervisory signal of the previous L2S model, we propose to use quantized self-supervised speech representations, named speech units, as an additional prediction target for the L2S model. Therefore, the proposed L2S model is trained to generate multiple targets, mel-spectrogram and speech units. As the speech units are discrete while mel-spectrogram is continuous, the proposed multi-target L2S model can be"},"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":"2305.19603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:17:32Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"c68ef3f71a23da86809987d3b02d2ccbae69c19afb544bc2d44c82f077562fc4","abstract_canon_sha256":"115f92a2b454d4b70e03dcd429f27207ca81f9132553bcdc190c1750766edf89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:52.748299Z","signature_b64":"bui9EoevdQ6Pj/OBOJoXw9nDT0KjWquahA0MVUE4ulNLvf/Gmtp11zdmrNnZZZ7nTEzCOu94gbV//CMR95O3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51fdffddb66e728774b8957de62856cbfb19c02a7fe3ea3b04ff653968761a0a","last_reissued_at":"2026-07-05T06:15:52.747792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:52.747792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intelligible Lip-to-Speech Synthesis with Speech Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jeongsoo Choi, Minsu Kim, Yong Man Ro","submitted_at":"2023-05-31T07:17:32Z","abstract_excerpt":"In this paper, we propose a novel Lip-to-Speech synthesis (L2S) framework, for synthesizing intelligible speech from a silent lip movement video. Specifically, to complement the insufficient supervisory signal of the previous L2S model, we propose to use quantized self-supervised speech representations, named speech units, as an additional prediction target for the L2S model. Therefore, the proposed L2S model is trained to generate multiple targets, mel-spectrogram and speech units. As the speech units are discrete while mel-spectrogram is continuous, the proposed multi-target L2S model can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19603","kind":"arxiv","version":1},"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/2305.19603/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":"2305.19603","created_at":"2026-07-05T06:15:52.747856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19603v1","created_at":"2026-07-05T06:15:52.747856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19603","created_at":"2026-07-05T06:15:52.747856+00:00"},{"alias_kind":"pith_short_12","alias_value":"KH677XNWNZZI","created_at":"2026-07-05T06:15:52.747856+00:00"},{"alias_kind":"pith_short_16","alias_value":"KH677XNWNZZIO5FY","created_at":"2026-07-05T06:15:52.747856+00:00"},{"alias_kind":"pith_short_8","alias_value":"KH677XNW","created_at":"2026-07-05T06:15:52.747856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00733","citing_title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP","json":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP.json","graph_json":"https://pith.science/api/pith-number/KH677XNWNZZIO5FYSV66MKCWZP/graph.json","events_json":"https://pith.science/api/pith-number/KH677XNWNZZIO5FYSV66MKCWZP/events.json","paper":"https://pith.science/paper/KH677XNW"},"agent_actions":{"view_html":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP","download_json":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP.json","view_paper":"https://pith.science/paper/KH677XNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19603&json=true","fetch_graph":"https://pith.science/api/pith-number/KH677XNWNZZIO5FYSV66MKCWZP/graph.json","fetch_events":"https://pith.science/api/pith-number/KH677XNWNZZIO5FYSV66MKCWZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/action/storage_attestation","attest_author":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/action/author_attestation","sign_citation":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/action/citation_signature","submit_replication":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/action/replication_record"}},"created_at":"2026-07-05T06:15:52.747856+00:00","updated_at":"2026-07-05T06:15:52.747856+00:00"}