{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZJNXL3OE4UI4VZDIG2QNI2QTN2","short_pith_number":"pith:ZJNXL3OE","schema_version":"1.0","canonical_sha256":"ca5b75edc4e511cae46836a0d46a136e80da928a0102a482c1962163c3b7f4d0","source":{"kind":"arxiv","id":"2002.08933","version":2},"attestation_state":"computed","paper":{"title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"David Grangier, Neil Zeghidour","submitted_at":"2020-02-20T18:30:36Z","abstract_excerpt":"We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to jointly perform both tasks from the raw waveform. Wavesplit infers a set of source representations via clustering, which addresses the fundamental permutation problem of separation. For speech separation, our sequence-wide speaker representations provide a more robust separation of long, challenging recordings compared to prior work. Wavesplit redefines the state"},"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":"2002.08933","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-20T18:30:36Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"a11a876e05adcef92cfacb6c15428c2f52b9027c4fdd3600b8bd7154e0ef7fe6","abstract_canon_sha256":"b6ef32cb6f48835127aeba587edbfce0e3f3a3452fd238b4b053010e41f83bd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:50.298581Z","signature_b64":"Fb/aOl1ERGPkGJ6A32XWFX3+KD4CYKVUTttm/kj0P5LO0s6Tw5LALINOBNyCDwm/hS0DO9WzIAr8PDrzk09lBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca5b75edc4e511cae46836a0d46a136e80da928a0102a482c1962163c3b7f4d0","last_reissued_at":"2026-07-05T01:15:50.298125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:50.298125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"David Grangier, Neil Zeghidour","submitted_at":"2020-02-20T18:30:36Z","abstract_excerpt":"We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to jointly perform both tasks from the raw waveform. Wavesplit infers a set of source representations via clustering, which addresses the fundamental permutation problem of separation. For speech separation, our sequence-wide speaker representations provide a more robust separation of long, challenging recordings compared to prior work. Wavesplit redefines the state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08933","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/2002.08933/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":"2002.08933","created_at":"2026-07-05T01:15:50.298187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.08933v2","created_at":"2026-07-05T01:15:50.298187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08933","created_at":"2026-07-05T01:15:50.298187+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJNXL3OE4UI4","created_at":"2026-07-05T01:15:50.298187+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJNXL3OE4UI4VZDI","created_at":"2026-07-05T01:15:50.298187+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJNXL3OE","created_at":"2026-07-05T01:15:50.298187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05207","citing_title":"SpectroStream: A Versatile Neural Codec for General Audio","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2","json":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2.json","graph_json":"https://pith.science/api/pith-number/ZJNXL3OE4UI4VZDIG2QNI2QTN2/graph.json","events_json":"https://pith.science/api/pith-number/ZJNXL3OE4UI4VZDIG2QNI2QTN2/events.json","paper":"https://pith.science/paper/ZJNXL3OE"},"agent_actions":{"view_html":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2","download_json":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2.json","view_paper":"https://pith.science/paper/ZJNXL3OE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.08933&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJNXL3OE4UI4VZDIG2QNI2QTN2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJNXL3OE4UI4VZDIG2QNI2QTN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2/action/storage_attestation","attest_author":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2/action/author_attestation","sign_citation":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2/action/citation_signature","submit_replication":"https://pith.science/pith/ZJNXL3OE4UI4VZDIG2QNI2QTN2/action/replication_record"}},"created_at":"2026-07-05T01:15:50.298187+00:00","updated_at":"2026-07-05T01:15:50.298187+00:00"}