{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HHBY2SZJBCEEYQFOCZMZ7ETLYN","short_pith_number":"pith:HHBY2SZJ","schema_version":"1.0","canonical_sha256":"39c38d4b2908884c40ae16599f926bc35ebbff77e168f6cf63cfca4c4db86cc7","source":{"kind":"arxiv","id":"2409.15799","version":1},"attestation_state":"computed","paper":{"title":"WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Jianwei Yu, Junjie Li, Ke Zhang, Meng Ge, Shaoxiong Lin, Shuai Wang, Xuefei Wang, Yanmin Qian","submitted_at":"2024-09-24T06:47:12Z","abstract_excerpt":"Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem. In recent years, TSE draws increasing attention due to its potential for various applications such as user-customized interfaces and hearing aids, or as a crutial front-end processing technologies for subsequential tasks such as speech recognition and speaker recongtion. However, there are currently few open-source toolkits or available pre-trained models for off-the-shelf usage. In this work, we introduce WeSe"},"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":"2409.15799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-24T06:47:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e0bea9eb14def801c3db5c3943efa9122babdbf973eb68116890d3baeba8c52d","abstract_canon_sha256":"51071aa748d250d712725802c0a1f508c2161b9ca33d89808f3440832cf167df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:00.450808Z","signature_b64":"qM2/VWqHBjQBmdLkT10VV5vbn+ZyiLLePC+9M419Aobdw60Is7qF/dptmZFXqta0Q0XoEF1j9FoO7u+qAb8NBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39c38d4b2908884c40ae16599f926bc35ebbff77e168f6cf63cfca4c4db86cc7","last_reissued_at":"2026-07-05T09:11:00.450306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:00.450306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Jianwei Yu, Junjie Li, Ke Zhang, Meng Ge, Shaoxiong Lin, Shuai Wang, Xuefei Wang, Yanmin Qian","submitted_at":"2024-09-24T06:47:12Z","abstract_excerpt":"Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem. In recent years, TSE draws increasing attention due to its potential for various applications such as user-customized interfaces and hearing aids, or as a crutial front-end processing technologies for subsequential tasks such as speech recognition and speaker recongtion. However, there are currently few open-source toolkits or available pre-trained models for off-the-shelf usage. In this work, we introduce WeSe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15799","kind":"arxiv","version":1},"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/2409.15799/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":"2409.15799","created_at":"2026-07-05T09:11:00.450389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15799v1","created_at":"2026-07-05T09:11:00.450389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15799","created_at":"2026-07-05T09:11:00.450389+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHBY2SZJBCEE","created_at":"2026-07-05T09:11:00.450389+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHBY2SZJBCEEYQFO","created_at":"2026-07-05T09:11:00.450389+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHBY2SZJ","created_at":"2026-07-05T09:11:00.450389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09510","citing_title":"Enhancing Target Speaker Extraction with Explicit Speaker Consistency Modeling","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN","json":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN.json","graph_json":"https://pith.science/api/pith-number/HHBY2SZJBCEEYQFOCZMZ7ETLYN/graph.json","events_json":"https://pith.science/api/pith-number/HHBY2SZJBCEEYQFOCZMZ7ETLYN/events.json","paper":"https://pith.science/paper/HHBY2SZJ"},"agent_actions":{"view_html":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN","download_json":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN.json","view_paper":"https://pith.science/paper/HHBY2SZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15799&json=true","fetch_graph":"https://pith.science/api/pith-number/HHBY2SZJBCEEYQFOCZMZ7ETLYN/graph.json","fetch_events":"https://pith.science/api/pith-number/HHBY2SZJBCEEYQFOCZMZ7ETLYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN/action/storage_attestation","attest_author":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN/action/author_attestation","sign_citation":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN/action/citation_signature","submit_replication":"https://pith.science/pith/HHBY2SZJBCEEYQFOCZMZ7ETLYN/action/replication_record"}},"created_at":"2026-07-05T09:11:00.450389+00:00","updated_at":"2026-07-05T09:11:00.450389+00:00"}