{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OFIEODV336QCENNSSHOL7NAVV7","short_pith_number":"pith:OFIEODV3","schema_version":"1.0","canonical_sha256":"7150470ebbdfa02235b291dcbfb415afc779ad61d5a818ebafc7380a174ad1da","source":{"kind":"arxiv","id":"1607.00325","version":2},"attestation_state":"computed","paper":{"title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2016-07-01T17:34:16Z","abstract_excerpt":"We propose a novel deep learning model, which supports permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from most of the prior arts that treat speech separation as a multi-class regression problem and the deep clustering technique that considers it a segmentation (or clustering) problem, our model optimizes for the separation regression error, ignoring the order of mixing sources. This strategy cleverly solves the long-lasting label permutation problem that has prevented progress on deep learni"},"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":"1607.00325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-01T17:34:16Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8e0cabf9030a2507abe038f99d1ecae801ad23f226f24a812f3a3c6b126029ae","abstract_canon_sha256":"7661da6fe72c8e1ba999386ec5e7260bbee1008fb5a75240511dc30a053497ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:03.919343Z","signature_b64":"EnQA55CNnWKI4fMGUQ9vBP9Y/ZIg0VmqkwAPGvyLF3vuvTP05yVKmD6HA1A2ry4dnpwKN6ANc1nuYJH81FG3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7150470ebbdfa02235b291dcbfb415afc779ad61d5a818ebafc7380a174ad1da","last_reissued_at":"2026-05-17T23:59:03.918835Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:03.918835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2016-07-01T17:34:16Z","abstract_excerpt":"We propose a novel deep learning model, which supports permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from most of the prior arts that treat speech separation as a multi-class regression problem and the deep clustering technique that considers it a segmentation (or clustering) problem, our model optimizes for the separation regression error, ignoring the order of mixing sources. This strategy cleverly solves the long-lasting label permutation problem that has prevented progress on deep learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00325","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":""},"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":"1607.00325","created_at":"2026-05-17T23:59:03.918908+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00325v2","created_at":"2026-05-17T23:59:03.918908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00325","created_at":"2026-05-17T23:59:03.918908+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFIEODV336QC","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFIEODV336QCENNS","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFIEODV3","created_at":"2026-05-18T12:30:36.002864+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/OFIEODV336QCENNSSHOL7NAVV7","json":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7.json","graph_json":"https://pith.science/api/pith-number/OFIEODV336QCENNSSHOL7NAVV7/graph.json","events_json":"https://pith.science/api/pith-number/OFIEODV336QCENNSSHOL7NAVV7/events.json","paper":"https://pith.science/paper/OFIEODV3"},"agent_actions":{"view_html":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7","download_json":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7.json","view_paper":"https://pith.science/paper/OFIEODV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00325&json=true","fetch_graph":"https://pith.science/api/pith-number/OFIEODV336QCENNSSHOL7NAVV7/graph.json","fetch_events":"https://pith.science/api/pith-number/OFIEODV336QCENNSSHOL7NAVV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7/action/storage_attestation","attest_author":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7/action/author_attestation","sign_citation":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7/action/citation_signature","submit_replication":"https://pith.science/pith/OFIEODV336QCENNSSHOL7NAVV7/action/replication_record"}},"created_at":"2026-05-17T23:59:03.918908+00:00","updated_at":"2026-05-17T23:59:03.918908+00:00"}