{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V3NP4IYA5H6CBZKLVXU36NXHMX","short_pith_number":"pith:V3NP4IYA","schema_version":"1.0","canonical_sha256":"aedafe2300e9fc20e54bade9bf36e765f960048047b90ade86913baab440a31b","source":{"kind":"arxiv","id":"2501.13465","version":1},"attestation_state":"computed","paper":{"title":"Neural Vocoders as Speech Enhancers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andong Li, Chengshi Zheng, Fengyuan Hao, Xiaodong Li, Zhihang Sun","submitted_at":"2025-01-23T08:27:01Z","abstract_excerpt":"Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \\textit{Can a model designed for one task's rank degradation be adapted for the other?} and \\textit{Is it possible to address both tasks using a unified model?} Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with perfo"},"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":"2501.13465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-23T08:27:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e2a47e57659e0040e2584e55fe65f0f011e39efa0b1278c3635810f26aaccfcd","abstract_canon_sha256":"f13f4783bf77747699b11697b04ef6cc0981ce45a8ec8a9442f0dcb376be0904"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:28.996855Z","signature_b64":"dS1Vk6Ltm1t+ziVs8WaH0Y1prpFh4r56kVLfjHDh0u44i0r7loC5YaiVjewkZ3ARDq79TPw/+BYYOueeTrYxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aedafe2300e9fc20e54bade9bf36e765f960048047b90ade86913baab440a31b","last_reissued_at":"2026-07-05T10:04:28.996376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:28.996376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Vocoders as Speech Enhancers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andong Li, Chengshi Zheng, Fengyuan Hao, Xiaodong Li, Zhihang Sun","submitted_at":"2025-01-23T08:27:01Z","abstract_excerpt":"Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \\textit{Can a model designed for one task's rank degradation be adapted for the other?} and \\textit{Is it possible to address both tasks using a unified model?} Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13465","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/2501.13465/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":"2501.13465","created_at":"2026-07-05T10:04:28.996432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13465v1","created_at":"2026-07-05T10:04:28.996432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13465","created_at":"2026-07-05T10:04:28.996432+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3NP4IYA5H6C","created_at":"2026-07-05T10:04:28.996432+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3NP4IYA5H6CBZKL","created_at":"2026-07-05T10:04:28.996432+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3NP4IYA","created_at":"2026-07-05T10:04:28.996432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20731","citing_title":"Learning Neural Vocoder from Range-Null Space Decomposition","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX","json":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX.json","graph_json":"https://pith.science/api/pith-number/V3NP4IYA5H6CBZKLVXU36NXHMX/graph.json","events_json":"https://pith.science/api/pith-number/V3NP4IYA5H6CBZKLVXU36NXHMX/events.json","paper":"https://pith.science/paper/V3NP4IYA"},"agent_actions":{"view_html":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX","download_json":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX.json","view_paper":"https://pith.science/paper/V3NP4IYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13465&json=true","fetch_graph":"https://pith.science/api/pith-number/V3NP4IYA5H6CBZKLVXU36NXHMX/graph.json","fetch_events":"https://pith.science/api/pith-number/V3NP4IYA5H6CBZKLVXU36NXHMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX/action/storage_attestation","attest_author":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX/action/author_attestation","sign_citation":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX/action/citation_signature","submit_replication":"https://pith.science/pith/V3NP4IYA5H6CBZKLVXU36NXHMX/action/replication_record"}},"created_at":"2026-07-05T10:04:28.996432+00:00","updated_at":"2026-07-05T10:04:28.996432+00:00"}