{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZCSSSUWMVI24RMH2ZPLEPTIOIN","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":"9024bac636ea685dd00aca7f65ae63c7f7718059d9612e700fc93fa65ad904eb","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T15:32:56Z","title_canon_sha256":"8e0d7e5e7662ee67f7e09b983541f0d43fe072c1b72820277f2f5530036c18d3"},"schema_version":"1.0","source":{"id":"2310.19644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19644","created_at":"2026-07-05T07:06:53Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19644v1","created_at":"2026-07-05T07:06:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19644","created_at":"2026-07-05T07:06:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZCSSSUWMVI24","created_at":"2026-07-05T07:06:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZCSSSUWMVI24RMH2","created_at":"2026-07-05T07:06:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZCSSSUWM","created_at":"2026-07-05T07:06:53Z"}],"graph_snapshots":[{"event_id":"sha256:ad68dc941dc7c6676412cf4fdcf121982b040c65832a8c231ce39f270bcae9ca","target":"graph","created_at":"2026-07-05T07:06:53Z","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/2310.19644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target speech extraction aims to extract, based on a given conditioning cue, a target speech signal that is corrupted by interfering sources, such as noise or competing speakers. Building upon the achievements of the state-of-the-art (SOTA) time-frequency speaker separation model TF-GridNet, we propose AV-GridNet, a visual-grounded variant that incorporates the face recording of a target speaker as a conditioning factor during the extraction process. Recognizing the inherent dissimilarities between speech and noise signals as interfering sources, we also propose SAV-GridNet, a scenario-aware m","authors_text":"Chiori Hori, Francois G. Germain, Gordon Wichern, Jonathan Le Roux, Sameer Khurana, Yoshiki Masuyama, Zexu Pan","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T15:32:56Z","title":"Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19644","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":"sha256:410a8c5e1ede1d8e34efb7ba8beeadd842d09ab1474fe7d63b1e81868ccf7978","target":"record","created_at":"2026-07-05T07:06:53Z","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":"9024bac636ea685dd00aca7f65ae63c7f7718059d9612e700fc93fa65ad904eb","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-30T15:32:56Z","title_canon_sha256":"8e0d7e5e7662ee67f7e09b983541f0d43fe072c1b72820277f2f5530036c18d3"},"schema_version":"1.0","source":{"id":"2310.19644","kind":"arxiv","version":1}},"canonical_sha256":"c8a52952ccaa35c8b0facbd647cd0e4340f4e7a36bb7a4df28634806011d2a44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8a52952ccaa35c8b0facbd647cd0e4340f4e7a36bb7a4df28634806011d2a44","first_computed_at":"2026-07-05T07:06:53.332981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:53.332981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U8x+mXWZFadEMtV3DXs0m7NXTBu7X/2daSVtF89Q/TYQ4UPYQFpIxTihFVoflaQT1/IPMFuGF76/9pwKXQ2sCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:53.333479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:410a8c5e1ede1d8e34efb7ba8beeadd842d09ab1474fe7d63b1e81868ccf7978","sha256:ad68dc941dc7c6676412cf4fdcf121982b040c65832a8c231ce39f270bcae9ca"],"state_sha256":"25c76670df4386e0bba3c2adf2860a737f331c5a46d8c29bc18c74063fb6765f"}