{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GBNRY4H46K6T3UAXZS3HIKV2AG","short_pith_number":"pith:GBNRY4H4","schema_version":"1.0","canonical_sha256":"305b1c70fcf2bd3dd017ccb6742aba01a5812e791609b17805b6d712991297db","source":{"kind":"arxiv","id":"2011.03426","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Sivaraman, Minje Kim","submitted_at":"2020-11-06T15:21:00Z","abstract_excerpt":"This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to cleaning recordings of a test-time speaker is limited to a few seconds, but noisy recordings of the speaker are abundant. We develop a simple contrastive learning procedure which treats the abundant noisy data as makeshift training targets through pairwise noise injection: the model is pretrained to maximize agreement between pairs of differently deformed iden"},"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":"2011.03426","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-06T15:21:00Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"eb96e92d113d38b7084affc0fe20d6586ae06e06385f5ecb7b95e5032153a891","abstract_canon_sha256":"5fb30765f93ff43f84f856fabbd417d71809fd64c2b5a92d314cc2f7effab016"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:22.271831Z","signature_b64":"weIJ9sraOGYzNeWq2MRHlc3zQ418Y4FfeMXz7+FXqkERjtM6o+HD3YTpI/tANVQ5KNUP1IUspJoDm7aVSjOBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305b1c70fcf2bd3dd017ccb6742aba01a5812e791609b17805b6d712991297db","last_reissued_at":"2026-07-05T04:47:22.271306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:22.271306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Sivaraman, Minje Kim","submitted_at":"2020-11-06T15:21:00Z","abstract_excerpt":"This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to cleaning recordings of a test-time speaker is limited to a few seconds, but noisy recordings of the speaker are abundant. We develop a simple contrastive learning procedure which treats the abundant noisy data as makeshift training targets through pairwise noise injection: the model is pretrained to maximize agreement between pairs of differently deformed iden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03426","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/2011.03426/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":"2011.03426","created_at":"2026-07-05T04:47:22.271370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.03426v2","created_at":"2026-07-05T04:47:22.271370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03426","created_at":"2026-07-05T04:47:22.271370+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBNRY4H46K6T","created_at":"2026-07-05T04:47:22.271370+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBNRY4H46K6T3UAX","created_at":"2026-07-05T04:47:22.271370+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBNRY4H4","created_at":"2026-07-05T04:47:22.271370+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/GBNRY4H46K6T3UAXZS3HIKV2AG","json":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG.json","graph_json":"https://pith.science/api/pith-number/GBNRY4H46K6T3UAXZS3HIKV2AG/graph.json","events_json":"https://pith.science/api/pith-number/GBNRY4H46K6T3UAXZS3HIKV2AG/events.json","paper":"https://pith.science/paper/GBNRY4H4"},"agent_actions":{"view_html":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG","download_json":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG.json","view_paper":"https://pith.science/paper/GBNRY4H4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.03426&json=true","fetch_graph":"https://pith.science/api/pith-number/GBNRY4H46K6T3UAXZS3HIKV2AG/graph.json","fetch_events":"https://pith.science/api/pith-number/GBNRY4H46K6T3UAXZS3HIKV2AG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG/action/storage_attestation","attest_author":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG/action/author_attestation","sign_citation":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG/action/citation_signature","submit_replication":"https://pith.science/pith/GBNRY4H46K6T3UAXZS3HIKV2AG/action/replication_record"}},"created_at":"2026-07-05T04:47:22.271370+00:00","updated_at":"2026-07-05T04:47:22.271370+00:00"}