{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I5QYZ3EEUX4JVOUTCKXJ6H7YM7","short_pith_number":"pith:I5QYZ3EE","schema_version":"1.0","canonical_sha256":"47618cec84a5f89aba9312ae9f1ff867d24e74483eb3e5966c2458e24d712cbe","source":{"kind":"arxiv","id":"2309.09028","version":1},"attestation_state":"computed","paper":{"title":"Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunlei Zhang, Dong Yu, Hao Zhang, Heming Wang, Meng Yu, Muqiao Yang, Yixuan Zhang, Zhongweiyang Xu","submitted_at":"2023-09-16T15:42:55Z","abstract_excerpt":"Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in real-world scenarios, hampering listening experiences. To address these challenges, we propose a novel approach that uses pre-trained generative methods to resynthesize clean, anechoic speech from degraded inputs. This study leverages pre-trained vocoder or codec models to synthesize high-quality speech while enhancing robustness in challenging scenarios. Gener"},"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":"2309.09028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T15:42:55Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1ca2d530e83cbfd2129209646087226fadfe67f02f20aed2316729920fbd5d51","abstract_canon_sha256":"5708393a717d4878cc44e2b025349f5e8f96117005e6e95a87b83af909bad4f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:33.154801Z","signature_b64":"cTGf9Xhqv/VxCFtEpOLbyqBLvnm7FvI+nzjH25wF8Z4aKXZmPMd7EKn1ff5bMoOLAh+3YJQp7E7bRiIam6BkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47618cec84a5f89aba9312ae9f1ff867d24e74483eb3e5966c2458e24d712cbe","last_reissued_at":"2026-07-05T06:51:33.154312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:33.154312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunlei Zhang, Dong Yu, Hao Zhang, Heming Wang, Meng Yu, Muqiao Yang, Yixuan Zhang, Zhongweiyang Xu","submitted_at":"2023-09-16T15:42:55Z","abstract_excerpt":"Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in real-world scenarios, hampering listening experiences. To address these challenges, we propose a novel approach that uses pre-trained generative methods to resynthesize clean, anechoic speech from degraded inputs. This study leverages pre-trained vocoder or codec models to synthesize high-quality speech while enhancing robustness in challenging scenarios. Gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09028","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/2309.09028/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":"2309.09028","created_at":"2026-07-05T06:51:33.154377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09028v1","created_at":"2026-07-05T06:51:33.154377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09028","created_at":"2026-07-05T06:51:33.154377+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5QYZ3EEUX4J","created_at":"2026-07-05T06:51:33.154377+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5QYZ3EEUX4JVOUT","created_at":"2026-07-05T06:51:33.154377+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5QYZ3EE","created_at":"2026-07-05T06:51:33.154377+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/I5QYZ3EEUX4JVOUTCKXJ6H7YM7","json":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7.json","graph_json":"https://pith.science/api/pith-number/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/graph.json","events_json":"https://pith.science/api/pith-number/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/events.json","paper":"https://pith.science/paper/I5QYZ3EE"},"agent_actions":{"view_html":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7","download_json":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7.json","view_paper":"https://pith.science/paper/I5QYZ3EE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09028&json=true","fetch_graph":"https://pith.science/api/pith-number/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/graph.json","fetch_events":"https://pith.science/api/pith-number/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/action/storage_attestation","attest_author":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/action/author_attestation","sign_citation":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/action/citation_signature","submit_replication":"https://pith.science/pith/I5QYZ3EEUX4JVOUTCKXJ6H7YM7/action/replication_record"}},"created_at":"2026-07-05T06:51:33.154377+00:00","updated_at":"2026-07-05T06:51:33.154377+00:00"}