{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3GV4LDNSKI3NPR53QRKV4AZSR6","short_pith_number":"pith:3GV4LDNS","schema_version":"1.0","canonical_sha256":"d9abc58db25236d7c7bb84555e03328fb48f77a8e692dc37b4a3f4512fc77e28","source":{"kind":"arxiv","id":"2210.15849","version":3},"attestation_state":"computed","paper":{"title":"Hierarchical speaker representation for target speaker extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Huaiwen Zhang, Kanghao Zhang, Shulin He, Wei Rao, Xueliang Zhang, Yang Yang, Yukai Ju","submitted_at":"2022-10-28T02:46:47Z","abstract_excerpt":"Target speaker extraction aims to isolate a specific speaker's voice from a composite of multiple sound sources, guided by an enrollment utterance or called anchor. Current methods predominantly derive speaker embeddings from the anchor and integrate them into the separation network to separate the voice of the target speaker. However, the representation of the speaker embedding is too simplistic, often being merely a 1*1024 vector. This dense information makes it difficult for the separation network to harness effectively. To address this limitation, we introduce a pioneering methodology call"},"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":"2210.15849","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-28T02:46:47Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1ba98ffc9167188346e31ee2784e533a52e8a4a42c90264d1a143a556897b9ea","abstract_canon_sha256":"c2ab2d219f32ff1b79c9e57813b699d0c404741733a788869b1c1773bd85b2a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:18.143193Z","signature_b64":"qOe0X5lZBTQEv98rSjr4+Ewd1NfWCldtrS/7BOzBylL18CSDJl80jUvmlBaXH+3A40zFJJ+llqGFqstpV5j3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9abc58db25236d7c7bb84555e03328fb48f77a8e692dc37b4a3f4512fc77e28","last_reissued_at":"2026-07-05T07:30:18.142794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:18.142794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical speaker representation for target speaker extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Huaiwen Zhang, Kanghao Zhang, Shulin He, Wei Rao, Xueliang Zhang, Yang Yang, Yukai Ju","submitted_at":"2022-10-28T02:46:47Z","abstract_excerpt":"Target speaker extraction aims to isolate a specific speaker's voice from a composite of multiple sound sources, guided by an enrollment utterance or called anchor. Current methods predominantly derive speaker embeddings from the anchor and integrate them into the separation network to separate the voice of the target speaker. However, the representation of the speaker embedding is too simplistic, often being merely a 1*1024 vector. This dense information makes it difficult for the separation network to harness effectively. To address this limitation, we introduce a pioneering methodology call"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15849","kind":"arxiv","version":3},"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/2210.15849/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":"2210.15849","created_at":"2026-07-05T07:30:18.142843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15849v3","created_at":"2026-07-05T07:30:18.142843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15849","created_at":"2026-07-05T07:30:18.142843+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GV4LDNSKI3N","created_at":"2026-07-05T07:30:18.142843+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GV4LDNSKI3NPR53","created_at":"2026-07-05T07:30:18.142843+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GV4LDNS","created_at":"2026-07-05T07:30:18.142843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6","json":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6.json","graph_json":"https://pith.science/api/pith-number/3GV4LDNSKI3NPR53QRKV4AZSR6/graph.json","events_json":"https://pith.science/api/pith-number/3GV4LDNSKI3NPR53QRKV4AZSR6/events.json","paper":"https://pith.science/paper/3GV4LDNS"},"agent_actions":{"view_html":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6","download_json":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6.json","view_paper":"https://pith.science/paper/3GV4LDNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15849&json=true","fetch_graph":"https://pith.science/api/pith-number/3GV4LDNSKI3NPR53QRKV4AZSR6/graph.json","fetch_events":"https://pith.science/api/pith-number/3GV4LDNSKI3NPR53QRKV4AZSR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6/action/storage_attestation","attest_author":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6/action/author_attestation","sign_citation":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6/action/citation_signature","submit_replication":"https://pith.science/pith/3GV4LDNSKI3NPR53QRKV4AZSR6/action/replication_record"}},"created_at":"2026-07-05T07:30:18.142843+00:00","updated_at":"2026-07-05T07:30:18.142843+00:00"}