{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A7USEK4EE6YZ6A65VRF7NHVPBD","short_pith_number":"pith:A7USEK4E","schema_version":"1.0","canonical_sha256":"07e9222b8427b19f03ddac4bf69eaf08e1d886ac722b41842838afa277a7d1e8","source":{"kind":"arxiv","id":"2606.23712","version":1},"attestation_state":"computed","paper":{"title":"Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.SP","authors_text":"Colombe Mboungou (MULTISPEECH), Jean-Eudes Ayilo (MULTISPEECH), Mostafa Sadeghi (MULTISPEECH), Romain Serizel (MULTISPEECH)","submitted_at":"2026-06-16T06:39:04Z","abstract_excerpt":"Audio-visual speech enhancement (AVSE) exploits visual cues such as lip movements to recover speech in noisy environments. Recent work introduced diffusion-based unsupervised AVSE, where a speech diffusion model conditioned on visual features via cross-attention is trained and used as a data-driven prior for posterior sampling-based speech enhancement. Despite promising performance over its audio-only counterpart, the impact of explicitly enforcing cross-modal alignment in the fusion remains unclear. In this work, we propose to augment the diffusion training objective with a contrastive audio-"},"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":"2606.23712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2026-06-16T06:39:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce25bf4e01d2694350f947b1090c5d9cd2bac45f37ad9af87eaa1e7540f6da85","abstract_canon_sha256":"e25710ffc01267b6511b3a969800146d0df384b7d527966ce884324ce1a8a48a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:24.030998Z","signature_b64":"mfFs3JcuORdDuR3MOaRYtb6nKGqCr3CL2txVBX+3IhJRXfTo7IV3aOAul/Umn9P1dIA2V6e7y6MdGje6hEqMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07e9222b8427b19f03ddac4bf69eaf08e1d886ac722b41842838afa277a7d1e8","last_reissued_at":"2026-06-24T00:14:24.030594Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:24.030594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.SP","authors_text":"Colombe Mboungou (MULTISPEECH), Jean-Eudes Ayilo (MULTISPEECH), Mostafa Sadeghi (MULTISPEECH), Romain Serizel (MULTISPEECH)","submitted_at":"2026-06-16T06:39:04Z","abstract_excerpt":"Audio-visual speech enhancement (AVSE) exploits visual cues such as lip movements to recover speech in noisy environments. Recent work introduced diffusion-based unsupervised AVSE, where a speech diffusion model conditioned on visual features via cross-attention is trained and used as a data-driven prior for posterior sampling-based speech enhancement. Despite promising performance over its audio-only counterpart, the impact of explicitly enforcing cross-modal alignment in the fusion remains unclear. In this work, we propose to augment the diffusion training objective with a contrastive audio-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23712","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/2606.23712/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":"2606.23712","created_at":"2026-06-24T00:14:24.030649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23712v1","created_at":"2026-06-24T00:14:24.030649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23712","created_at":"2026-06-24T00:14:24.030649+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7USEK4EE6YZ","created_at":"2026-06-24T00:14:24.030649+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7USEK4EE6YZ6A65","created_at":"2026-06-24T00:14:24.030649+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7USEK4E","created_at":"2026-06-24T00:14:24.030649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.23712","citing_title":"Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD","json":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD.json","graph_json":"https://pith.science/api/pith-number/A7USEK4EE6YZ6A65VRF7NHVPBD/graph.json","events_json":"https://pith.science/api/pith-number/A7USEK4EE6YZ6A65VRF7NHVPBD/events.json","paper":"https://pith.science/paper/A7USEK4E"},"agent_actions":{"view_html":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD","download_json":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD.json","view_paper":"https://pith.science/paper/A7USEK4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23712&json=true","fetch_graph":"https://pith.science/api/pith-number/A7USEK4EE6YZ6A65VRF7NHVPBD/graph.json","fetch_events":"https://pith.science/api/pith-number/A7USEK4EE6YZ6A65VRF7NHVPBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD/action/storage_attestation","attest_author":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD/action/author_attestation","sign_citation":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD/action/citation_signature","submit_replication":"https://pith.science/pith/A7USEK4EE6YZ6A65VRF7NHVPBD/action/replication_record"}},"created_at":"2026-06-24T00:14:24.030649+00:00","updated_at":"2026-06-24T00:14:24.030649+00:00"}