{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VUXLSGKOCTT7SVN6J323EECDRK","short_pith_number":"pith:VUXLSGKO","schema_version":"1.0","canonical_sha256":"ad2eb9194e14e7f955be4ef5b210438a9e8f2f849b74be23cfc172e7c1368451","source":{"kind":"arxiv","id":"2409.02489","version":2},"attestation_state":"computed","paper":{"title":"NeuroSpex: Neuro-Guided Speaker Extraction with Cross-Modal Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dashanka De Silva, Haizhou Li, Saurav Pahuja, Siqi Cai, Tanja Schultz","submitted_at":"2024-09-04T07:33:01Z","abstract_excerpt":"In the study of auditory attention, it has been revealed that there exists a robust correlation between attended speech and elicited neural responses, measurable through electroencephalography (EEG). Therefore, it is possible to use the attention information available within EEG signals to guide the extraction of the target speaker in a cocktail party computationally. In this paper, we present a neuro-guided speaker extraction model, i.e. NeuroSpex, using the EEG response of the listener as the sole auxiliary reference cue to extract attended speech from monaural speech mixtures. We propose a "},"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":"2409.02489","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-04T07:33:01Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"d4bd76f8b95e8dd0430d50aa54c8ea4ad452fc4eb93cf8edc3b2e1655a441cf8","abstract_canon_sha256":"d619dce3e94c7d98ce32a6c0408d7c960ede2fd8ca6b4782ad68500c3acd0234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:31.403417Z","signature_b64":"hSdfqWPpA02MeGUn1uec5VvYYRL0Si/sJBTTWSB+8wCJ6enWryY2Gzi8isiLEzPCC6Rzzrtspn9cogLtfHfDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad2eb9194e14e7f955be4ef5b210438a9e8f2f849b74be23cfc172e7c1368451","last_reissued_at":"2026-07-05T09:07:31.402914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:31.402914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuroSpex: Neuro-Guided Speaker Extraction with Cross-Modal Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dashanka De Silva, Haizhou Li, Saurav Pahuja, Siqi Cai, Tanja Schultz","submitted_at":"2024-09-04T07:33:01Z","abstract_excerpt":"In the study of auditory attention, it has been revealed that there exists a robust correlation between attended speech and elicited neural responses, measurable through electroencephalography (EEG). Therefore, it is possible to use the attention information available within EEG signals to guide the extraction of the target speaker in a cocktail party computationally. In this paper, we present a neuro-guided speaker extraction model, i.e. NeuroSpex, using the EEG response of the listener as the sole auxiliary reference cue to extract attended speech from monaural speech mixtures. We propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02489","kind":"arxiv","version":2},"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/2409.02489/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":"2409.02489","created_at":"2026-07-05T09:07:31.402980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02489v2","created_at":"2026-07-05T09:07:31.402980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02489","created_at":"2026-07-05T09:07:31.402980+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUXLSGKOCTT7","created_at":"2026-07-05T09:07:31.402980+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUXLSGKOCTT7SVN6","created_at":"2026-07-05T09:07:31.402980+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUXLSGKO","created_at":"2026-07-05T09:07:31.402980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00466","citing_title":"M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK","json":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK.json","graph_json":"https://pith.science/api/pith-number/VUXLSGKOCTT7SVN6J323EECDRK/graph.json","events_json":"https://pith.science/api/pith-number/VUXLSGKOCTT7SVN6J323EECDRK/events.json","paper":"https://pith.science/paper/VUXLSGKO"},"agent_actions":{"view_html":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK","download_json":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK.json","view_paper":"https://pith.science/paper/VUXLSGKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02489&json=true","fetch_graph":"https://pith.science/api/pith-number/VUXLSGKOCTT7SVN6J323EECDRK/graph.json","fetch_events":"https://pith.science/api/pith-number/VUXLSGKOCTT7SVN6J323EECDRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK/action/storage_attestation","attest_author":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK/action/author_attestation","sign_citation":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK/action/citation_signature","submit_replication":"https://pith.science/pith/VUXLSGKOCTT7SVN6J323EECDRK/action/replication_record"}},"created_at":"2026-07-05T09:07:31.402980+00:00","updated_at":"2026-07-05T09:07:31.402980+00:00"}