{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N23WRFTZW2VI5ENBYEBPRGDLDF","short_pith_number":"pith:N23WRFTZ","schema_version":"1.0","canonical_sha256":"6eb7689679b6aa8e91a1c102f8986b196ebdaa5ce0c23e2c66f20693b3d5f7a4","source":{"kind":"arxiv","id":"2111.05703","version":1},"attestation_state":"computed","paper":{"title":"OSSEM: one-shot speaker adaptive speech enhancement using meta learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cheng Yu, Mirco Ravanelli, Szu-Wei Fu, Tsun-An Hsieh, Yu Tsao","submitted_at":"2021-11-10T14:21:28Z","abstract_excerpt":"Although deep learning (DL) has achieved notable progress in speech enhancement (SE), further research is still required for a DL-based SE system to adapt effectively and efficiently to particular speakers. In this study, we propose a novel meta-learning-based speaker-adaptive SE approach (called OSSEM) that aims to achieve SE model adaptation in a one-shot manner. OSSEM consists of a modified transformer SE network and a speaker-specific masking (SSM) network. In practice, the SSM network takes an enrolled speaker embedding extracted using ECAPA-TDNN to adjust the input noisy feature through "},"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":"2111.05703","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-11-10T14:21:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"299ea96e44fde2699a0cbdb4ed26c80341fbcd8f86b6125a8b9fb3f09d46d5c0","abstract_canon_sha256":"fcf30e50da4aefdf34f6d2ecac5f0a9e11cbb256bad025da41daec1d00dc6ff4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:47.273954Z","signature_b64":"EmuqDZ31kp43D1CDE0dziH5MycRCf44TSCtTEjwX5Adt0w6L1Ij0WIAJlSh9iGh5mlO8tlysGzadM8ENGxAuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb7689679b6aa8e91a1c102f8986b196ebdaa5ce0c23e2c66f20693b3d5f7a4","last_reissued_at":"2026-07-05T03:30:47.273555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:47.273555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSSEM: one-shot speaker adaptive speech enhancement using meta learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cheng Yu, Mirco Ravanelli, Szu-Wei Fu, Tsun-An Hsieh, Yu Tsao","submitted_at":"2021-11-10T14:21:28Z","abstract_excerpt":"Although deep learning (DL) has achieved notable progress in speech enhancement (SE), further research is still required for a DL-based SE system to adapt effectively and efficiently to particular speakers. In this study, we propose a novel meta-learning-based speaker-adaptive SE approach (called OSSEM) that aims to achieve SE model adaptation in a one-shot manner. OSSEM consists of a modified transformer SE network and a speaker-specific masking (SSM) network. In practice, the SSM network takes an enrolled speaker embedding extracted using ECAPA-TDNN to adjust the input noisy feature through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05703","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/2111.05703/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":"2111.05703","created_at":"2026-07-05T03:30:47.273617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05703v1","created_at":"2026-07-05T03:30:47.273617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05703","created_at":"2026-07-05T03:30:47.273617+00:00"},{"alias_kind":"pith_short_12","alias_value":"N23WRFTZW2VI","created_at":"2026-07-05T03:30:47.273617+00:00"},{"alias_kind":"pith_short_16","alias_value":"N23WRFTZW2VI5ENB","created_at":"2026-07-05T03:30:47.273617+00:00"},{"alias_kind":"pith_short_8","alias_value":"N23WRFTZ","created_at":"2026-07-05T03:30:47.273617+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/N23WRFTZW2VI5ENBYEBPRGDLDF","json":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF.json","graph_json":"https://pith.science/api/pith-number/N23WRFTZW2VI5ENBYEBPRGDLDF/graph.json","events_json":"https://pith.science/api/pith-number/N23WRFTZW2VI5ENBYEBPRGDLDF/events.json","paper":"https://pith.science/paper/N23WRFTZ"},"agent_actions":{"view_html":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF","download_json":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF.json","view_paper":"https://pith.science/paper/N23WRFTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05703&json=true","fetch_graph":"https://pith.science/api/pith-number/N23WRFTZW2VI5ENBYEBPRGDLDF/graph.json","fetch_events":"https://pith.science/api/pith-number/N23WRFTZW2VI5ENBYEBPRGDLDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF/action/storage_attestation","attest_author":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF/action/author_attestation","sign_citation":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF/action/citation_signature","submit_replication":"https://pith.science/pith/N23WRFTZW2VI5ENBYEBPRGDLDF/action/replication_record"}},"created_at":"2026-07-05T03:30:47.273617+00:00","updated_at":"2026-07-05T03:30:47.273617+00:00"}