{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KH677XNWNZZIO5FYSV66MKCWZP","short_pith_number":"pith:KH677XNW","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"},"canonical_sha256":"51fdffddb66e728774b8957de62856cbfb19c02a7fe3ea3b04ff653968761a0a","source":{"kind":"arxiv","id":"2305.19603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19603","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19603v1","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19603","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"KH677XNWNZZI","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"KH677XNWNZZIO5FY","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"KH677XNW","created_at":"2026-07-05T06:15:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KH677XNWNZZIO5FYSV66MKCWZP","target":"record","payload":{"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"},"canonical_sha256":"51fdffddb66e728774b8957de62856cbfb19c02a7fe3ea3b04ff653968761a0a","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"},"source_kind":"arxiv","source_id":"2305.19603","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ql5fheX+92SdLEZZcwxkEKjMa/dCr0uxEzyPFYckj76LSxAco2hvd1IT2BAQYFMpneLcpgHa4ZJ0oZ7FJcCICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:04.740256Z"},"content_sha256":"3e7091773678bc760140d315d3b754ee74d85d943ffa2c0f859bede0852a9cac","schema_version":"1.0","event_id":"sha256:3e7091773678bc760140d315d3b754ee74d85d943ffa2c0f859bede0852a9cac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KH677XNWNZZIO5FYSV66MKCWZP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beGkkYErZqGUsrqBzo0PAvv7tV715lS0HeGsQv4wUTMkuy2egClUCI1JdlojpJPQgLQ9ozvBpJi+X4Voev7eBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:04.740767Z"},"content_sha256":"63be55737002aca5f09245563fbc0efa39923a60c1324027c24d2348dd37c99c","schema_version":"1.0","event_id":"sha256:63be55737002aca5f09245563fbc0efa39923a60c1324027c24d2348dd37c99c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/bundle.json","state_url":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KH677XNWNZZIO5FYSV66MKCWZP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:52:04Z","links":{"resolver":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP","bundle":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/bundle.json","state":"https://pith.science/pith/KH677XNWNZZIO5FYSV66MKCWZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KH677XNWNZZIO5FYSV66MKCWZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KH677XNWNZZIO5FYSV66MKCWZP","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":"115f92a2b454d4b70e03dcd429f27207ca81f9132553bcdc190c1750766edf89","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:17:32Z","title_canon_sha256":"c68ef3f71a23da86809987d3b02d2ccbae69c19afb544bc2d44c82f077562fc4"},"schema_version":"1.0","source":{"id":"2305.19603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19603","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19603v1","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19603","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"KH677XNWNZZI","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"KH677XNWNZZIO5FY","created_at":"2026-07-05T06:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"KH677XNW","created_at":"2026-07-05T06:15:52Z"}],"graph_snapshots":[{"event_id":"sha256:63be55737002aca5f09245563fbc0efa39923a60c1324027c24d2348dd37c99c","target":"graph","created_at":"2026-07-05T06:15:52Z","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/2305.19603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jeongsoo Choi, Minsu Kim, Yong Man Ro","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:17:32Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19603","kind":"arxiv","version":1},"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":"sha256:3e7091773678bc760140d315d3b754ee74d85d943ffa2c0f859bede0852a9cac","target":"record","created_at":"2026-07-05T06:15:52Z","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":"115f92a2b454d4b70e03dcd429f27207ca81f9132553bcdc190c1750766edf89","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T07:17:32Z","title_canon_sha256":"c68ef3f71a23da86809987d3b02d2ccbae69c19afb544bc2d44c82f077562fc4"},"schema_version":"1.0","source":{"id":"2305.19603","kind":"arxiv","version":1}},"canonical_sha256":"51fdffddb66e728774b8957de62856cbfb19c02a7fe3ea3b04ff653968761a0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51fdffddb66e728774b8957de62856cbfb19c02a7fe3ea3b04ff653968761a0a","first_computed_at":"2026-07-05T06:15:52.747792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:52.747792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bui9EoevdQ6Pj/OBOJoXw9nDT0KjWquahA0MVUE4ulNLvf/Gmtp11zdmrNnZZZ7nTEzCOu94gbV//CMR95O3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:52.748299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e7091773678bc760140d315d3b754ee74d85d943ffa2c0f859bede0852a9cac","sha256:63be55737002aca5f09245563fbc0efa39923a60c1324027c24d2348dd37c99c"],"state_sha256":"b0e4dbd05812522e2dde89c5d52ceca72d10b15a2551fde314ea2ad7da8fd8ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0UphUhF87N4F3emgPnHvR8xlxx2ETaiJJTnkc31Hae8dXhHGli4bzq3AH9wfGS3/GoI+SPdOgXz+E04ImOh1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:52:04.746098Z","bundle_sha256":"4e7646d93b285c0e77a6035f65eb80e91f910d9653149749dba5c67112d31fa4"}}