{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GNK6QMHYHINWJ5KJ2CWL6QLCCU","short_pith_number":"pith:GNK6QMHY","schema_version":"1.0","canonical_sha256":"3355e830f83a1b64f549d0acbf41621506c425fbb42bc199d09206ea86f23fea","source":{"kind":"arxiv","id":"2202.00733","version":2},"attestation_state":"computed","paper":{"title":"New Insights on Target Speaker Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emanu\\\"el A. P. Habets, Mohamed Elminshawi, Soumitro Chakrabarty, Srikanth Raj Chetupalli, Wolfgang Mack","submitted_at":"2022-02-01T20:10:23Z","abstract_excerpt":"Speaker extraction (SE) aims to segregate the speech of a target speaker from a mixture of interfering speakers with the help of auxiliary information. Several forms of auxiliary information have been employed in single-channel SE, such as a speech snippet enrolled from the target speaker or visual information corresponding to the spoken utterance. The effectiveness of the auxiliary information in SE is typically evaluated by comparing the extraction performance of SE with uninformed speaker separation (SS) methods. Following this evaluation protocol, many SE studies have reported performance "},"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":"2202.00733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-01T20:10:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3562f7b1588221b045596246b248c7e82337e51b47269dc00fe5e15a70a3abd6","abstract_canon_sha256":"1239a663778cd006ca2bf8f5244ae48dc01dfaae9b7b37ded0fd0284951872a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:51.237403Z","signature_b64":"ol0yx1lr9CWEcpeccMsSMHLy0Hwxx3Zll63t4vaBcwwxgwIO2Ic7OSaKjhJ0He8BxDY5wS3CeDhGPof1/+PcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3355e830f83a1b64f549d0acbf41621506c425fbb42bc199d09206ea86f23fea","last_reissued_at":"2026-07-05T06:50:51.236964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:51.236964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Insights on Target Speaker Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emanu\\\"el A. P. Habets, Mohamed Elminshawi, Soumitro Chakrabarty, Srikanth Raj Chetupalli, Wolfgang Mack","submitted_at":"2022-02-01T20:10:23Z","abstract_excerpt":"Speaker extraction (SE) aims to segregate the speech of a target speaker from a mixture of interfering speakers with the help of auxiliary information. Several forms of auxiliary information have been employed in single-channel SE, such as a speech snippet enrolled from the target speaker or visual information corresponding to the spoken utterance. The effectiveness of the auxiliary information in SE is typically evaluated by comparing the extraction performance of SE with uninformed speaker separation (SS) methods. Following this evaluation protocol, many SE studies have reported performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00733","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/2202.00733/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":"2202.00733","created_at":"2026-07-05T06:50:51.237021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00733v2","created_at":"2026-07-05T06:50:51.237021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00733","created_at":"2026-07-05T06:50:51.237021+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNK6QMHYHINW","created_at":"2026-07-05T06:50:51.237021+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNK6QMHYHINWJ5KJ","created_at":"2026-07-05T06:50:51.237021+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNK6QMHY","created_at":"2026-07-05T06:50:51.237021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.06006","citing_title":"Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU","json":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU.json","graph_json":"https://pith.science/api/pith-number/GNK6QMHYHINWJ5KJ2CWL6QLCCU/graph.json","events_json":"https://pith.science/api/pith-number/GNK6QMHYHINWJ5KJ2CWL6QLCCU/events.json","paper":"https://pith.science/paper/GNK6QMHY"},"agent_actions":{"view_html":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU","download_json":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU.json","view_paper":"https://pith.science/paper/GNK6QMHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00733&json=true","fetch_graph":"https://pith.science/api/pith-number/GNK6QMHYHINWJ5KJ2CWL6QLCCU/graph.json","fetch_events":"https://pith.science/api/pith-number/GNK6QMHYHINWJ5KJ2CWL6QLCCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU/action/storage_attestation","attest_author":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU/action/author_attestation","sign_citation":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU/action/citation_signature","submit_replication":"https://pith.science/pith/GNK6QMHYHINWJ5KJ2CWL6QLCCU/action/replication_record"}},"created_at":"2026-07-05T06:50:51.237021+00:00","updated_at":"2026-07-05T06:50:51.237021+00:00"}