{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J7RRMFVYXILGZRKJDYP4IQNQ2A","short_pith_number":"pith:J7RRMFVY","schema_version":"1.0","canonical_sha256":"4fe31616b8ba166cc5491e1fc441b0d018078c61faff09efe9464afcd4340eca","source":{"kind":"arxiv","id":"2507.21448","version":2},"attestation_state":"computed","paper":{"title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"eess.AS","authors_text":"Li-Chia Yang, Shuo Zhang, Sile Yin, T. Aleksandra Ma","submitted_at":"2025-07-29T02:38:56Z","abstract_excerpt":"Speech enhancement in audio-only settings remains challenging, particularly in the presence of interfering speakers. This paper presents a simple yet effective real-time audio-visual speech enhancement (AVSE) system, RAVEN, which isolates and enhances the on-screen target speaker while suppressing interfering speakers and background noise. We investigate how visual embeddings learned from audio-visual speech recognition (AVSR) and active speaker detection (ASD) contribute to AVSE across different SNR conditions and numbers of interfering speakers. Our results show concatenating embeddings from"},"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":"2507.21448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-29T02:38:56Z","cross_cats_sorted":["cs.ET","cs.LG"],"title_canon_sha256":"fa1ce44eeb446671c05893cc43d9c0926cd01e29896b558710c4b3f7718535d4","abstract_canon_sha256":"900888096a3c38bbe99619e3ee695ac9a4d07ad6738d34b5827e35447cb235e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:06.217982Z","signature_b64":"o9EpoUHsiUL1/W41jNfjhMeHwKADA4I0QLbrNqGVwhKeifLmAbR7+QypvG9VN1How1qJh3T8/xQJVAjket8AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fe31616b8ba166cc5491e1fc441b0d018078c61faff09efe9464afcd4340eca","last_reissued_at":"2026-07-05T11:48:06.217487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:06.217487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"eess.AS","authors_text":"Li-Chia Yang, Shuo Zhang, Sile Yin, T. Aleksandra Ma","submitted_at":"2025-07-29T02:38:56Z","abstract_excerpt":"Speech enhancement in audio-only settings remains challenging, particularly in the presence of interfering speakers. This paper presents a simple yet effective real-time audio-visual speech enhancement (AVSE) system, RAVEN, which isolates and enhances the on-screen target speaker while suppressing interfering speakers and background noise. We investigate how visual embeddings learned from audio-visual speech recognition (AVSR) and active speaker detection (ASD) contribute to AVSE across different SNR conditions and numbers of interfering speakers. Our results show concatenating embeddings from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21448","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/2507.21448/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":"2507.21448","created_at":"2026-07-05T11:48:06.217543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21448v2","created_at":"2026-07-05T11:48:06.217543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21448","created_at":"2026-07-05T11:48:06.217543+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7RRMFVYXILG","created_at":"2026-07-05T11:48:06.217543+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7RRMFVYXILGZRKJ","created_at":"2026-07-05T11:48:06.217543+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7RRMFVY","created_at":"2026-07-05T11:48:06.217543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13931","citing_title":"FSD50K-Solo: Automated Curation of Single-Source Sound Events","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A","json":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A.json","graph_json":"https://pith.science/api/pith-number/J7RRMFVYXILGZRKJDYP4IQNQ2A/graph.json","events_json":"https://pith.science/api/pith-number/J7RRMFVYXILGZRKJDYP4IQNQ2A/events.json","paper":"https://pith.science/paper/J7RRMFVY"},"agent_actions":{"view_html":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A","download_json":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A.json","view_paper":"https://pith.science/paper/J7RRMFVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21448&json=true","fetch_graph":"https://pith.science/api/pith-number/J7RRMFVYXILGZRKJDYP4IQNQ2A/graph.json","fetch_events":"https://pith.science/api/pith-number/J7RRMFVYXILGZRKJDYP4IQNQ2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A/action/storage_attestation","attest_author":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A/action/author_attestation","sign_citation":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A/action/citation_signature","submit_replication":"https://pith.science/pith/J7RRMFVYXILGZRKJDYP4IQNQ2A/action/replication_record"}},"created_at":"2026-07-05T11:48:06.217543+00:00","updated_at":"2026-07-05T11:48:06.217543+00:00"}