{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5OGIM3B6H24VQF2BTCVXMVQ6AU","short_pith_number":"pith:5OGIM3B6","schema_version":"1.0","canonical_sha256":"eb8c866c3e3eb958174198ab76561e053fd36d535238a0bb9b9d24562a7eb49c","source":{"kind":"arxiv","id":"2104.02017","version":2},"attestation_state":"computed","paper":{"title":"Efficient Personalized Speech Enhancement through Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Sivaraman, Minje Kim","submitted_at":"2021-04-05T17:12:51Z","abstract_excerpt":"This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their enhancement function towards a particular speaker's voice, expecting to solve a narrower problem. Hence, specialists are capable of achieving more optimal performance in addition to reducing computational complexity. However, naive personalization methods can require clean speech from the target user, which is inconvenient to acquire, e.g., due to subpar recordin"},"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":"2104.02017","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T17:12:51Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"0ae17d7a0df70bb4ee1272aa7594c7b7295403198470eb8cdbd6fa08b0a0944a","abstract_canon_sha256":"a6de137afd777431c9dfe694dcba74febde0aa7ad8e4e92807e4552037ab5218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:56.599597Z","signature_b64":"7a6veqDKXwUZnbE0w2+oFrg3t/604Ndp+UDBQs2xZs/5EbOsmbuEjJATYhJQEeBLAi4lOJTiFJeU+lbRDrd2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb8c866c3e3eb958174198ab76561e053fd36d535238a0bb9b9d24562a7eb49c","last_reissued_at":"2026-07-05T04:43:56.599126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:56.599126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Personalized Speech Enhancement through Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Sivaraman, Minje Kim","submitted_at":"2021-04-05T17:12:51Z","abstract_excerpt":"This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their enhancement function towards a particular speaker's voice, expecting to solve a narrower problem. Hence, specialists are capable of achieving more optimal performance in addition to reducing computational complexity. However, naive personalization methods can require clean speech from the target user, which is inconvenient to acquire, e.g., due to subpar recordin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02017","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/2104.02017/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":"2104.02017","created_at":"2026-07-05T04:43:56.599208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02017v2","created_at":"2026-07-05T04:43:56.599208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02017","created_at":"2026-07-05T04:43:56.599208+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OGIM3B6H24V","created_at":"2026-07-05T04:43:56.599208+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OGIM3B6H24VQF2B","created_at":"2026-07-05T04:43:56.599208+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OGIM3B6","created_at":"2026-07-05T04:43:56.599208+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/5OGIM3B6H24VQF2BTCVXMVQ6AU","json":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU.json","graph_json":"https://pith.science/api/pith-number/5OGIM3B6H24VQF2BTCVXMVQ6AU/graph.json","events_json":"https://pith.science/api/pith-number/5OGIM3B6H24VQF2BTCVXMVQ6AU/events.json","paper":"https://pith.science/paper/5OGIM3B6"},"agent_actions":{"view_html":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU","download_json":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU.json","view_paper":"https://pith.science/paper/5OGIM3B6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02017&json=true","fetch_graph":"https://pith.science/api/pith-number/5OGIM3B6H24VQF2BTCVXMVQ6AU/graph.json","fetch_events":"https://pith.science/api/pith-number/5OGIM3B6H24VQF2BTCVXMVQ6AU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU/action/storage_attestation","attest_author":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU/action/author_attestation","sign_citation":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU/action/citation_signature","submit_replication":"https://pith.science/pith/5OGIM3B6H24VQF2BTCVXMVQ6AU/action/replication_record"}},"created_at":"2026-07-05T04:43:56.599208+00:00","updated_at":"2026-07-05T04:43:56.599208+00:00"}