{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SYUCBDWRUMUUEWGXMNM7JMZAVZ","short_pith_number":"pith:SYUCBDWR","schema_version":"1.0","canonical_sha256":"9628208ed1a3294258d76359f4b320ae6a08cff4e098f0ca3122e7df69ebc424","source":{"kind":"arxiv","id":"2310.19581","version":1},"attestation_state":"computed","paper":{"title":"Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chaeyoung Jung, Jaehun Kim, Joon Son Chung, Suyeon Lee, Youngjoon Jang","submitted_at":"2023-10-30T14:39:34Z","abstract_excerpt":"The objective of this work is to extract target speaker's voice from a mixture of voices using visual cues. Existing works on audio-visual speech separation have demonstrated their performance with promising intelligibility, but maintaining naturalness remains a challenge. To address this issue, we propose AVDiffuSS, an audio-visual speech separation model based on a diffusion mechanism known for its capability in generating natural samples. For an effective fusion of the two modalities for diffusion, we also propose a cross-attention-based feature fusion mechanism. This mechanism is specifica"},"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":"2310.19581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T14:39:34Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"455d134f8692716e5faf67608ae74c14da891e953c102290628e2b8b14dd5e35","abstract_canon_sha256":"7f3f5b47d56a5292df1a96f123507bbd63a19222f355c07457704d12edf9e3cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:52.621329Z","signature_b64":"8zJnGbzM1rF6PBDI+gGcQHP/JPMOW+cRYqxuvDECVtk/WdXw1D3Ma4B4P21dOiOINgqHBkPy/GthZNXGY7D7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9628208ed1a3294258d76359f4b320ae6a08cff4e098f0ca3122e7df69ebc424","last_reissued_at":"2026-07-05T07:06:52.620846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:52.620846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chaeyoung Jung, Jaehun Kim, Joon Son Chung, Suyeon Lee, Youngjoon Jang","submitted_at":"2023-10-30T14:39:34Z","abstract_excerpt":"The objective of this work is to extract target speaker's voice from a mixture of voices using visual cues. Existing works on audio-visual speech separation have demonstrated their performance with promising intelligibility, but maintaining naturalness remains a challenge. To address this issue, we propose AVDiffuSS, an audio-visual speech separation model based on a diffusion mechanism known for its capability in generating natural samples. For an effective fusion of the two modalities for diffusion, we also propose a cross-attention-based feature fusion mechanism. This mechanism is specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19581","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/2310.19581/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":"2310.19581","created_at":"2026-07-05T07:06:52.620904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19581v1","created_at":"2026-07-05T07:06:52.620904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19581","created_at":"2026-07-05T07:06:52.620904+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYUCBDWRUMUU","created_at":"2026-07-05T07:06:52.620904+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYUCBDWRUMUUEWGX","created_at":"2026-07-05T07:06:52.620904+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYUCBDWR","created_at":"2026-07-05T07:06:52.620904+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/SYUCBDWRUMUUEWGXMNM7JMZAVZ","json":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ.json","graph_json":"https://pith.science/api/pith-number/SYUCBDWRUMUUEWGXMNM7JMZAVZ/graph.json","events_json":"https://pith.science/api/pith-number/SYUCBDWRUMUUEWGXMNM7JMZAVZ/events.json","paper":"https://pith.science/paper/SYUCBDWR"},"agent_actions":{"view_html":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ","download_json":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ.json","view_paper":"https://pith.science/paper/SYUCBDWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19581&json=true","fetch_graph":"https://pith.science/api/pith-number/SYUCBDWRUMUUEWGXMNM7JMZAVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SYUCBDWRUMUUEWGXMNM7JMZAVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ/action/storage_attestation","attest_author":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ/action/author_attestation","sign_citation":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ/action/citation_signature","submit_replication":"https://pith.science/pith/SYUCBDWRUMUUEWGXMNM7JMZAVZ/action/replication_record"}},"created_at":"2026-07-05T07:06:52.620904+00:00","updated_at":"2026-07-05T07:06:52.620904+00:00"}