{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HV2IICLOF7WTMP5TKECFHOHUGN","short_pith_number":"pith:HV2IICLO","schema_version":"1.0","canonical_sha256":"3d7484096e2fed363fb3510453b8f4337b200a47e221e5cdb10ae0d2a8791f0e","source":{"kind":"arxiv","id":"2409.07841","version":3},"attestation_state":"computed","paper":{"title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bang Zeng, Beilong Tang, Ming Li","submitted_at":"2024-09-12T08:41:07Z","abstract_excerpt":"We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. E"},"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":"2409.07841","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T08:41:07Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d0ccc253c4d44112ea69c051149a3978c4b746bacabcf50f71c9cc18aefbe947","abstract_canon_sha256":"3c55b19a342270e8c555f47527c291b3735a4825b10b15c5fc3b1352b646ed9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:51.214498Z","signature_b64":"/GzktnzI3y4lBidAXjJIBcRRVE5OK8AzSJq2lJU8e0VVkc1ZyPA1bLAzSOhe4ANe2fl5rcXbMDynDFItQhiFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7484096e2fed363fb3510453b8f4337b200a47e221e5cdb10ae0d2a8791f0e","last_reissued_at":"2026-07-05T09:07:51.214053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:51.214053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bang Zeng, Beilong Tang, Ming Li","submitted_at":"2024-09-12T08:41:07Z","abstract_excerpt":"We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07841","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/2409.07841/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":"2409.07841","created_at":"2026-07-05T09:07:51.214106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07841v3","created_at":"2026-07-05T09:07:51.214106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07841","created_at":"2026-07-05T09:07:51.214106+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV2IICLOF7WT","created_at":"2026-07-05T09:07:51.214106+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV2IICLOF7WTMP5T","created_at":"2026-07-05T09:07:51.214106+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV2IICLO","created_at":"2026-07-05T09:07:51.214106+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":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN","json":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN.json","graph_json":"https://pith.science/api/pith-number/HV2IICLOF7WTMP5TKECFHOHUGN/graph.json","events_json":"https://pith.science/api/pith-number/HV2IICLOF7WTMP5TKECFHOHUGN/events.json","paper":"https://pith.science/paper/HV2IICLO"},"agent_actions":{"view_html":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN","download_json":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN.json","view_paper":"https://pith.science/paper/HV2IICLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07841&json=true","fetch_graph":"https://pith.science/api/pith-number/HV2IICLOF7WTMP5TKECFHOHUGN/graph.json","fetch_events":"https://pith.science/api/pith-number/HV2IICLOF7WTMP5TKECFHOHUGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN/action/storage_attestation","attest_author":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN/action/author_attestation","sign_citation":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN/action/citation_signature","submit_replication":"https://pith.science/pith/HV2IICLOF7WTMP5TKECFHOHUGN/action/replication_record"}},"created_at":"2026-07-05T09:07:51.214106+00:00","updated_at":"2026-07-05T09:07:51.214106+00:00"}