{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GJ5HK3KBB6BPEOXS2VDFK5BJTH","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":"73140e26e86d3ef35f323869c017b49468993f03199f870aa8f8263389f584bc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","title_canon_sha256":"5d37de8aa6cb9bfebd3780a4d0d06ddbcf78b2c40dcffcbd6a0844ad210f99cd"},"schema_version":"1.0","source":{"id":"2406.11619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11619","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11619v1","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11619","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"GJ5HK3KBB6BP","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"GJ5HK3KBB6BPEOXS","created_at":"2026-07-05T08:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"GJ5HK3KB","created_at":"2026-07-05T08:32:55Z"}],"graph_snapshots":[{"event_id":"sha256:2af4c10757d94f9472f1f1cb8fb352bd7673872fd55c25befb4251267c14996c","target":"graph","created_at":"2026-07-05T08:32:55Z","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/2406.11619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal co","authors_text":"Anurag Kumar, Buye Xu, Cheng Yu, Deliang Wang, Ke Tan, Vahid Ahmadi Kalkhorani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","title":"AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11619","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:fe4239a44340967748574ebb8c4d0c2430421bc3e9d045a63b44537c1cb68483","target":"record","created_at":"2026-07-05T08:32:55Z","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":"73140e26e86d3ef35f323869c017b49468993f03199f870aa8f8263389f584bc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T15:04:15Z","title_canon_sha256":"5d37de8aa6cb9bfebd3780a4d0d06ddbcf78b2c40dcffcbd6a0844ad210f99cd"},"schema_version":"1.0","source":{"id":"2406.11619","kind":"arxiv","version":1}},"canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"327a756d410f82f23af2d54655742999c4c1a5baef44868b66f86fe935a0587b","first_computed_at":"2026-07-05T08:32:55.645299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:55.645299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QDcfb0KAMsnRgkvg/3Nmiss08kX2wJdESwDOisnS9Khz4brj+WngQ43cmUXRnDkdcx0xyDDWEWaE/s4FtWDqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:55.645773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe4239a44340967748574ebb8c4d0c2430421bc3e9d045a63b44537c1cb68483","sha256:2af4c10757d94f9472f1f1cb8fb352bd7673872fd55c25befb4251267c14996c"],"state_sha256":"4bf598217aa8aa0fc98423ae83bd8344ddfbbdd914a909cc209efeeef1592b5a"}