{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DXKRG35LGSFIF4SGJIAQFA24JA","short_pith_number":"pith:DXKRG35L","schema_version":"1.0","canonical_sha256":"1dd5136fab348a82f2464a0102835c483a91c00aba644b1804e41ca0d26e3224","source":{"kind":"arxiv","id":"2601.06006","version":2},"attestation_state":"computed","paper":{"title":"Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bang Zeng, Beilong Tang, Ming Li, Wang Xiang","submitted_at":"2026-01-09T18:41:12Z","abstract_excerpt":"Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE and SE systems are based on discriminative modeling and have shown strong interference suppression ability, but they often remain limited in perceptual quality and naturalness. To address this issue, we first introduce LauraTSE, a generative TSE model built on an autoregressive decoder-only language model. Although generative modeling is promising for quality"},"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":"2601.06006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-09T18:41:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"89f7807ec448b40e03d684bb8c9f475178e1ac485139111dbbf7b44367d8a6a0","abstract_canon_sha256":"e4c7edd87baeef71ca0551fb52c8d2a7654ac8b0e43cf94b3106cdc84cced5ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:04:56.963225Z","signature_b64":"DRHlbdaSEsZrM9L4p1G5nfHTzL3HoeKaE/38ExpALCzB4BV+qSxnCbLvKwdQaS3cvGfxuzTjdc5BGUrwrXvcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dd5136fab348a82f2464a0102835c483a91c00aba644b1804e41ca0d26e3224","last_reissued_at":"2026-05-21T02:04:56.962412Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:04:56.962412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bang Zeng, Beilong Tang, Ming Li, Wang Xiang","submitted_at":"2026-01-09T18:41:12Z","abstract_excerpt":"Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE and SE systems are based on discriminative modeling and have shown strong interference suppression ability, but they often remain limited in perceptual quality and naturalness. To address this issue, we first introduce LauraTSE, a generative TSE model built on an autoregressive decoder-only language model. Although generative modeling is promising for quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06006","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/2601.06006/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":"2601.06006","created_at":"2026-05-21T02:04:56.962547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.06006v2","created_at":"2026-05-21T02:04:56.962547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06006","created_at":"2026-05-21T02:04:56.962547+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXKRG35LGSFI","created_at":"2026-05-21T02:04:56.962547+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXKRG35LGSFIF4SG","created_at":"2026-05-21T02:04:56.962547+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXKRG35L","created_at":"2026-05-21T02:04:56.962547+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/DXKRG35LGSFIF4SGJIAQFA24JA","json":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA.json","graph_json":"https://pith.science/api/pith-number/DXKRG35LGSFIF4SGJIAQFA24JA/graph.json","events_json":"https://pith.science/api/pith-number/DXKRG35LGSFIF4SGJIAQFA24JA/events.json","paper":"https://pith.science/paper/DXKRG35L"},"agent_actions":{"view_html":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA","download_json":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA.json","view_paper":"https://pith.science/paper/DXKRG35L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.06006&json=true","fetch_graph":"https://pith.science/api/pith-number/DXKRG35LGSFIF4SGJIAQFA24JA/graph.json","fetch_events":"https://pith.science/api/pith-number/DXKRG35LGSFIF4SGJIAQFA24JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA/action/storage_attestation","attest_author":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA/action/author_attestation","sign_citation":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA/action/citation_signature","submit_replication":"https://pith.science/pith/DXKRG35LGSFIF4SGJIAQFA24JA/action/replication_record"}},"created_at":"2026-05-21T02:04:56.962547+00:00","updated_at":"2026-05-21T02:04:56.962547+00:00"}