{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:57KQXBIS4CSIBS3MBYDZMGA3IN","short_pith_number":"pith:57KQXBIS","schema_version":"1.0","canonical_sha256":"efd50b8512e0a480cb6c0e0796181b434b0f7d70d5f7085e683b29838a2ef4ee","source":{"kind":"arxiv","id":"2505.06660","version":1},"attestation_state":"computed","paper":{"title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jan \\v{C}ernock\\'y, Junyi Peng, Marc Delcroix, Oldrich Plchot, Shoko Araki, Takanori Ashihara, Tsubasa Ochiai","submitted_at":"2025-05-10T14:23:37Z","abstract_excerpt":"Self-supervised learning (SSL) models have significantly advanced speech processing tasks, and several benchmarks have been proposed to validate their effectiveness. However, previous benchmarks have primarily focused on single-speaker scenarios, with less exploration of target-speaker tasks in noisy, multi-talker conditions -- a more challenging yet practical case. In this paper, we introduce the Target-Speaker Speech Processing Universal Performance Benchmark (TS-SUPERB), which includes four widely recognized target-speaker processing tasks that require identifying the target speaker and ext"},"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":"2505.06660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T14:23:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"93f82e686b4df00ce756db7a99b004b3fc9eee616854f19bc2e685d8d0df1fb8","abstract_canon_sha256":"df2e7ebc13367566b1b23c043c31310b009d0bc2e6ede5ad48d4384b60731b75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:13.837226Z","signature_b64":"tKQRQOgarqFouXYdibidAOrs3s1W36cOwJJe21Q6ZAAzB/3g7gFT12aFQPzCdRfW1bt7Ytsiw/X4n4LG/7N2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd50b8512e0a480cb6c0e0796181b434b0f7d70d5f7085e683b29838a2ef4ee","last_reissued_at":"2026-07-05T11:01:13.836754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:13.836754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jan \\v{C}ernock\\'y, Junyi Peng, Marc Delcroix, Oldrich Plchot, Shoko Araki, Takanori Ashihara, Tsubasa Ochiai","submitted_at":"2025-05-10T14:23:37Z","abstract_excerpt":"Self-supervised learning (SSL) models have significantly advanced speech processing tasks, and several benchmarks have been proposed to validate their effectiveness. However, previous benchmarks have primarily focused on single-speaker scenarios, with less exploration of target-speaker tasks in noisy, multi-talker conditions -- a more challenging yet practical case. In this paper, we introduce the Target-Speaker Speech Processing Universal Performance Benchmark (TS-SUPERB), which includes four widely recognized target-speaker processing tasks that require identifying the target speaker and ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06660","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/2505.06660/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":"2505.06660","created_at":"2026-07-05T11:01:13.836811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06660v1","created_at":"2026-07-05T11:01:13.836811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06660","created_at":"2026-07-05T11:01:13.836811+00:00"},{"alias_kind":"pith_short_12","alias_value":"57KQXBIS4CSI","created_at":"2026-07-05T11:01:13.836811+00:00"},{"alias_kind":"pith_short_16","alias_value":"57KQXBIS4CSIBS3M","created_at":"2026-07-05T11:01:13.836811+00:00"},{"alias_kind":"pith_short_8","alias_value":"57KQXBIS","created_at":"2026-07-05T11:01:13.836811+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/57KQXBIS4CSIBS3MBYDZMGA3IN","json":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN.json","graph_json":"https://pith.science/api/pith-number/57KQXBIS4CSIBS3MBYDZMGA3IN/graph.json","events_json":"https://pith.science/api/pith-number/57KQXBIS4CSIBS3MBYDZMGA3IN/events.json","paper":"https://pith.science/paper/57KQXBIS"},"agent_actions":{"view_html":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN","download_json":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN.json","view_paper":"https://pith.science/paper/57KQXBIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06660&json=true","fetch_graph":"https://pith.science/api/pith-number/57KQXBIS4CSIBS3MBYDZMGA3IN/graph.json","fetch_events":"https://pith.science/api/pith-number/57KQXBIS4CSIBS3MBYDZMGA3IN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN/action/storage_attestation","attest_author":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN/action/author_attestation","sign_citation":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN/action/citation_signature","submit_replication":"https://pith.science/pith/57KQXBIS4CSIBS3MBYDZMGA3IN/action/replication_record"}},"created_at":"2026-07-05T11:01:13.836811+00:00","updated_at":"2026-07-05T11:01:13.836811+00:00"}