{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NSVGFUDYDPAY2NAA6EUUZG3UFO","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":"402040cab6272cf73d1b038dfb66c1b9e0355755b225b04369f4120376935840","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T19:53:25Z","title_canon_sha256":"e752f7855076195dac60eccaebd845c3e186054b11e167cd8a8b0365e5d61d63"},"schema_version":"1.0","source":{"id":"2501.01518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01518","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01518v1","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01518","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"NSVGFUDYDPAY","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"NSVGFUDYDPAY2NAA","created_at":"2026-07-05T09:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"NSVGFUDY","created_at":"2026-07-05T09:56:26Z"}],"graph_snapshots":[{"event_id":"sha256:018501990e293db7c95bf60a6a1c63ba847686876a92629762b7ff6f906ee43d","target":"graph","created_at":"2026-07-05T09:56:26Z","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/2501.01518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is speech separation and enhancement in multi-speaker and noisy environments using a combination of different modalities. Previous works have shown good performance when conditioning on temporal or static visual evidence such as synchronised lip movements or face identity. In this paper, we present a unified framework for multi-modal speech separation and enhancement based on synchronous or asynchronous cues. To that end we make the following contributions: (i) we design a modern Transformer-based architecture tailored to fuse different modalities to solve the speech sep","authors_text":"Akam Rahimi, Andrew Zisserman, Triantafyllos Afouras","cross_cats":["cs.SD","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T19:53:25Z","title":"Reading to Listen at the Cocktail Party: Multi-Modal Speech Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01518","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":"sha256:975d58a76eb29b43d92bf4514f603c3d1920d258ec2a061d499b2367ae59119c","target":"record","created_at":"2026-07-05T09:56:26Z","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":"402040cab6272cf73d1b038dfb66c1b9e0355755b225b04369f4120376935840","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T19:53:25Z","title_canon_sha256":"e752f7855076195dac60eccaebd845c3e186054b11e167cd8a8b0365e5d61d63"},"schema_version":"1.0","source":{"id":"2501.01518","kind":"arxiv","version":1}},"canonical_sha256":"6caa62d0781bc18d3400f1294c9b742bb1a01c34ab9e6e883789c0ebf4c6db8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6caa62d0781bc18d3400f1294c9b742bb1a01c34ab9e6e883789c0ebf4c6db8b","first_computed_at":"2026-07-05T09:56:26.045800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:26.045800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TiyF2DAl2yneW2GN3Ty4xyMsgMayQOFh3sx+QoQyMNBSwe/kpuw+8Nh1AHzBpDSxwCG6kFDWzfSIyHTJx5QBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:26.046252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:975d58a76eb29b43d92bf4514f603c3d1920d258ec2a061d499b2367ae59119c","sha256:018501990e293db7c95bf60a6a1c63ba847686876a92629762b7ff6f906ee43d"],"state_sha256":"3e98ec76f703c5ff544f68c762b799af80109d90d080ccf2ffdbb7f1919a787c"}