{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:L7EXJR7R35NWX7NEFAA2LASH2S","short_pith_number":"pith:L7EXJR7R","schema_version":"1.0","canonical_sha256":"5fc974c7f1df5b6bfda42801a58247d4aba6e75da59c8801bfea9d14ce689b44","source":{"kind":"arxiv","id":"2005.14435","version":2},"attestation_state":"computed","paper":{"title":"Sub-Band Knowledge Distillation Framework for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Guanglai Gao, Shixue Wen, Xiangdong Su, Xiang Hao, Xiaofei Li, Yun Liu","submitted_at":"2020-05-29T07:55:12Z","abstract_excerpt":"In single-channel speech enhancement, methods based on full-band spectral features have been widely studied. However, only a few methods pay attention to non-full-band spectral features. In this paper, we explore a knowledge distillation framework based on sub-band spectral mapping for single-channel speech enhancement. Specifically, we divide the full frequency band into multiple sub-bands and pre-train an elite-level sub-band enhancement model (teacher model) for each sub-band. These teacher models are dedicated to processing their own sub-bands. Next, under the teacher models' guidance, we "},"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":"2005.14435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-29T07:55:12Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"524dafdc24af4190c18c24b9a9ab08a831a1f82d23bb41436bfff1f46c921a3d","abstract_canon_sha256":"4b1aa0e39bd8d510c844012225e4abef5d1e71b5fd3555c435098fb295c25316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:30.745479Z","signature_b64":"wij2g01TYrRuhSHW9KuB9W9500Iaft2l9Se19d6XMe140qTI6OmjmOVerWUIIPMsjiqc/2bHLGeo2h/quF+XCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fc974c7f1df5b6bfda42801a58247d4aba6e75da59c8801bfea9d14ce689b44","last_reissued_at":"2026-07-05T01:47:30.744919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:30.744919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sub-Band Knowledge Distillation Framework for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Guanglai Gao, Shixue Wen, Xiangdong Su, Xiang Hao, Xiaofei Li, Yun Liu","submitted_at":"2020-05-29T07:55:12Z","abstract_excerpt":"In single-channel speech enhancement, methods based on full-band spectral features have been widely studied. However, only a few methods pay attention to non-full-band spectral features. In this paper, we explore a knowledge distillation framework based on sub-band spectral mapping for single-channel speech enhancement. Specifically, we divide the full frequency band into multiple sub-bands and pre-train an elite-level sub-band enhancement model (teacher model) for each sub-band. These teacher models are dedicated to processing their own sub-bands. Next, under the teacher models' guidance, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14435","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/2005.14435/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":"2005.14435","created_at":"2026-07-05T01:47:30.744994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.14435v2","created_at":"2026-07-05T01:47:30.744994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14435","created_at":"2026-07-05T01:47:30.744994+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7EXJR7R35NW","created_at":"2026-07-05T01:47:30.744994+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7EXJR7R35NWX7NE","created_at":"2026-07-05T01:47:30.744994+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7EXJR7R","created_at":"2026-07-05T01:47:30.744994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00405","citing_title":"SaD: A Scenario-Aware Discriminator for Speech Enhancement","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S","json":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S.json","graph_json":"https://pith.science/api/pith-number/L7EXJR7R35NWX7NEFAA2LASH2S/graph.json","events_json":"https://pith.science/api/pith-number/L7EXJR7R35NWX7NEFAA2LASH2S/events.json","paper":"https://pith.science/paper/L7EXJR7R"},"agent_actions":{"view_html":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S","download_json":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S.json","view_paper":"https://pith.science/paper/L7EXJR7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.14435&json=true","fetch_graph":"https://pith.science/api/pith-number/L7EXJR7R35NWX7NEFAA2LASH2S/graph.json","fetch_events":"https://pith.science/api/pith-number/L7EXJR7R35NWX7NEFAA2LASH2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S/action/storage_attestation","attest_author":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S/action/author_attestation","sign_citation":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S/action/citation_signature","submit_replication":"https://pith.science/pith/L7EXJR7R35NWX7NEFAA2LASH2S/action/replication_record"}},"created_at":"2026-07-05T01:47:30.744994+00:00","updated_at":"2026-07-05T01:47:30.744994+00:00"}