{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3CDF2R2R4VIK4KQGQGECRZSLJM","short_pith_number":"pith:3CDF2R2R","schema_version":"1.0","canonical_sha256":"d8865d4751e550ae2a06818828e64b4b25b8052af1a97900027326de586f4f09","source":{"kind":"arxiv","id":"2410.16059","version":2},"attestation_state":"computed","paper":{"title":"Multi-Level Speaker Representation for 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, Junjie Li, Ke Zhang, Shuai Wang, Yangjie Wei, Yannan Wang, Yi Wang","submitted_at":"2024-10-21T14:38:20Z","abstract_excerpt":"Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model'"},"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":"2410.16059","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-21T14:38:20Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8bc1a3d33d6f5d7ed5d8362afffd61afbd9fc753d2193292061162b8441b5a42","abstract_canon_sha256":"4f0dfce4410c8cedbe7d100a9322cb44076b1b0742b17f449fa1322769b6a6a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:35.619517Z","signature_b64":"W5uuDUIj99E/1tSgNptoJWCxzj+ykIx8yFgipXxJC7zU9lTQTgclGhma2XgHUWF9IfZZc8WHmk20dDRMIJ+eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8865d4751e550ae2a06818828e64b4b25b8052af1a97900027326de586f4f09","last_reissued_at":"2026-07-05T09:47:35.618952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:35.618952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Level Speaker Representation for 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, Junjie Li, Ke Zhang, Shuai Wang, Yangjie Wei, Yannan Wang, Yi Wang","submitted_at":"2024-10-21T14:38:20Z","abstract_excerpt":"Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16059","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/2410.16059/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":"2410.16059","created_at":"2026-07-05T09:47:35.619014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16059v2","created_at":"2026-07-05T09:47:35.619014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16059","created_at":"2026-07-05T09:47:35.619014+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CDF2R2R4VIK","created_at":"2026-07-05T09:47:35.619014+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CDF2R2R4VIK4KQG","created_at":"2026-07-05T09:47:35.619014+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CDF2R2R","created_at":"2026-07-05T09:47:35.619014+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/3CDF2R2R4VIK4KQGQGECRZSLJM","json":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM.json","graph_json":"https://pith.science/api/pith-number/3CDF2R2R4VIK4KQGQGECRZSLJM/graph.json","events_json":"https://pith.science/api/pith-number/3CDF2R2R4VIK4KQGQGECRZSLJM/events.json","paper":"https://pith.science/paper/3CDF2R2R"},"agent_actions":{"view_html":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM","download_json":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM.json","view_paper":"https://pith.science/paper/3CDF2R2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16059&json=true","fetch_graph":"https://pith.science/api/pith-number/3CDF2R2R4VIK4KQGQGECRZSLJM/graph.json","fetch_events":"https://pith.science/api/pith-number/3CDF2R2R4VIK4KQGQGECRZSLJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM/action/storage_attestation","attest_author":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM/action/author_attestation","sign_citation":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM/action/citation_signature","submit_replication":"https://pith.science/pith/3CDF2R2R4VIK4KQGQGECRZSLJM/action/replication_record"}},"created_at":"2026-07-05T09:47:35.619014+00:00","updated_at":"2026-07-05T09:47:35.619014+00:00"}