{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SYUCBDWRUMUUEWGXMNM7JMZAVZ","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":"7f3f5b47d56a5292df1a96f123507bbd63a19222f355c07457704d12edf9e3cd","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T14:39:34Z","title_canon_sha256":"455d134f8692716e5faf67608ae74c14da891e953c102290628e2b8b14dd5e35"},"schema_version":"1.0","source":{"id":"2310.19581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19581","created_at":"2026-07-05T07:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19581v1","created_at":"2026-07-05T07:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19581","created_at":"2026-07-05T07:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"SYUCBDWRUMUU","created_at":"2026-07-05T07:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"SYUCBDWRUMUUEWGX","created_at":"2026-07-05T07:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"SYUCBDWR","created_at":"2026-07-05T07:06:52Z"}],"graph_snapshots":[{"event_id":"sha256:ab0714d3b032b121535cb07089b7f83d4551c4398b58022373a5f86153189ea8","target":"graph","created_at":"2026-07-05T07:06:52Z","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/2310.19581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaeyoung Jung, Jaehun Kim, Joon Son Chung, Suyeon Lee, Youngjoon Jang","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T14:39:34Z","title":"Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19581","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":"sha256:013f8d437f356a1a9d57e6433f905839c2517774f67aba6733030805c6a5c8bb","target":"record","created_at":"2026-07-05T07:06:52Z","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":"7f3f5b47d56a5292df1a96f123507bbd63a19222f355c07457704d12edf9e3cd","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T14:39:34Z","title_canon_sha256":"455d134f8692716e5faf67608ae74c14da891e953c102290628e2b8b14dd5e35"},"schema_version":"1.0","source":{"id":"2310.19581","kind":"arxiv","version":1}},"canonical_sha256":"9628208ed1a3294258d76359f4b320ae6a08cff4e098f0ca3122e7df69ebc424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9628208ed1a3294258d76359f4b320ae6a08cff4e098f0ca3122e7df69ebc424","first_computed_at":"2026-07-05T07:06:52.620846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:52.620846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zJnGbzM1rF6PBDI+gGcQHP/JPMOW+cRYqxuvDECVtk/WdXw1D3Ma4B4P21dOiOINgqHBkPy/GthZNXGY7D7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:52.621329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:013f8d437f356a1a9d57e6433f905839c2517774f67aba6733030805c6a5c8bb","sha256:ab0714d3b032b121535cb07089b7f83d4551c4398b58022373a5f86153189ea8"],"state_sha256":"7c4356dee3e174ab962b7289c9804d177ce764087364c118c42ac6676b75fb78"}