{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XFREMA62RWHFEQQTYW6UOWLNGA","short_pith_number":"pith:XFREMA62","schema_version":"1.0","canonical_sha256":"b9624603da8d8e524213c5bd47596d3030cff68812494183aeba8a671c7a3076","source":{"kind":"arxiv","id":"2311.12199","version":1},"attestation_state":"computed","paper":{"title":"Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenyang Gao, Ivan Marsic, Yue Gu","submitted_at":"2023-11-20T21:37:38Z","abstract_excerpt":"In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments. To address this issue, we propose a novel training strategy, dynamic sample dropout (DSD), which considers previous best label assignments and evaluation metrics to exclude the samples that may negatively impact the learned label assignments during traini"},"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":"2311.12199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-20T21:37:38Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2a8e11fa3b40b6149a09d31b8d9a2108c6958aee4fde6b6224bd0fa7f859a18c","abstract_canon_sha256":"1c4bb76d52f36fd9b23653055708ef6140b3f65455200837740a8131233225a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:01.909727Z","signature_b64":"GZrIAIK+QuHdIPgHYMkiyQKj58G/NvnoCOTBQff5+P3gKtdaoDKIjyJKjB9n9dUKfJGsUpwgrEkL7flIREVgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9624603da8d8e524213c5bd47596d3030cff68812494183aeba8a671c7a3076","last_reissued_at":"2026-07-05T07:15:01.909394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:01.909394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenyang Gao, Ivan Marsic, Yue Gu","submitted_at":"2023-11-20T21:37:38Z","abstract_excerpt":"In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments. To address this issue, we propose a novel training strategy, dynamic sample dropout (DSD), which considers previous best label assignments and evaluation metrics to exclude the samples that may negatively impact the learned label assignments during traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12199","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/2311.12199/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":"2311.12199","created_at":"2026-07-05T07:15:01.909448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12199v1","created_at":"2026-07-05T07:15:01.909448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12199","created_at":"2026-07-05T07:15:01.909448+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFREMA62RWHF","created_at":"2026-07-05T07:15:01.909448+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFREMA62RWHFEQQT","created_at":"2026-07-05T07:15:01.909448+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFREMA62","created_at":"2026-07-05T07:15:01.909448+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/XFREMA62RWHFEQQTYW6UOWLNGA","json":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA.json","graph_json":"https://pith.science/api/pith-number/XFREMA62RWHFEQQTYW6UOWLNGA/graph.json","events_json":"https://pith.science/api/pith-number/XFREMA62RWHFEQQTYW6UOWLNGA/events.json","paper":"https://pith.science/paper/XFREMA62"},"agent_actions":{"view_html":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA","download_json":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA.json","view_paper":"https://pith.science/paper/XFREMA62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12199&json=true","fetch_graph":"https://pith.science/api/pith-number/XFREMA62RWHFEQQTYW6UOWLNGA/graph.json","fetch_events":"https://pith.science/api/pith-number/XFREMA62RWHFEQQTYW6UOWLNGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA/action/storage_attestation","attest_author":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA/action/author_attestation","sign_citation":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA/action/citation_signature","submit_replication":"https://pith.science/pith/XFREMA62RWHFEQQTYW6UOWLNGA/action/replication_record"}},"created_at":"2026-07-05T07:15:01.909448+00:00","updated_at":"2026-07-05T07:15:01.909448+00:00"}