{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CAN62Q3W2DXHVQXRJXAMZGPWD7","short_pith_number":"pith:CAN62Q3W","schema_version":"1.0","canonical_sha256":"101bed4376d0ee7ac2f14dc0cc99f61ff19866fd8d63543d25de179c46470ae8","source":{"kind":"arxiv","id":"2501.00794","version":1},"attestation_state":"computed","paper":{"title":"VoiceRestore: Flow-Matching Transformers for Speech Recording Quality Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Stanislav Kirdey","submitted_at":"2025-01-01T10:13:19Z","abstract_excerpt":"We present VoiceRestore, a novel approach to restoring the quality of speech recordings using flow-matching Transformers trained in a self-supervised manner on synthetic data. Our method tackles a wide range of degradations frequently found in both short and long-form speech recordings, including background noise, reverberation, compression artifacts, and bandwidth limitations - all within a single, unified model. Leveraging conditional flow matching and classifier free guidance, the model learns to map degraded speech to high quality recordings without requiring paired clean and degraded data"},"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":"2501.00794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-01T10:13:19Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"adda1e6c5f2c2448f8ebc8b3e6999268d69e8b3f86db3a97b1549f630b0636d7","abstract_canon_sha256":"8fd3b234b7549e3eb9442a2462740c29cb678acc779e59fe0a5f8352d660bc20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:10.338198Z","signature_b64":"RyghnjfwIJn4zkfX/kYdOGvKtob5o2sTdQOgXuJHtlRiB5eXcjJEw4h9zWgL/CWvc/fypXWQ4dLuOdMFcQwUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"101bed4376d0ee7ac2f14dc0cc99f61ff19866fd8d63543d25de179c46470ae8","last_reissued_at":"2026-07-05T09:56:10.337760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:10.337760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoiceRestore: Flow-Matching Transformers for Speech Recording Quality Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Stanislav Kirdey","submitted_at":"2025-01-01T10:13:19Z","abstract_excerpt":"We present VoiceRestore, a novel approach to restoring the quality of speech recordings using flow-matching Transformers trained in a self-supervised manner on synthetic data. Our method tackles a wide range of degradations frequently found in both short and long-form speech recordings, including background noise, reverberation, compression artifacts, and bandwidth limitations - all within a single, unified model. Leveraging conditional flow matching and classifier free guidance, the model learns to map degraded speech to high quality recordings without requiring paired clean and degraded data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00794","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/2501.00794/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":"2501.00794","created_at":"2026-07-05T09:56:10.337820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00794v1","created_at":"2026-07-05T09:56:10.337820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00794","created_at":"2026-07-05T09:56:10.337820+00:00"},{"alias_kind":"pith_short_12","alias_value":"CAN62Q3W2DXH","created_at":"2026-07-05T09:56:10.337820+00:00"},{"alias_kind":"pith_short_16","alias_value":"CAN62Q3W2DXHVQXR","created_at":"2026-07-05T09:56:10.337820+00:00"},{"alias_kind":"pith_short_8","alias_value":"CAN62Q3W","created_at":"2026-07-05T09:56:10.337820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05575","citing_title":"SB-RF: Schr\\\"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancement","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05575","citing_title":"SB-RF: Schr\\\"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancement","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13563","citing_title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7","json":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7.json","graph_json":"https://pith.science/api/pith-number/CAN62Q3W2DXHVQXRJXAMZGPWD7/graph.json","events_json":"https://pith.science/api/pith-number/CAN62Q3W2DXHVQXRJXAMZGPWD7/events.json","paper":"https://pith.science/paper/CAN62Q3W"},"agent_actions":{"view_html":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7","download_json":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7.json","view_paper":"https://pith.science/paper/CAN62Q3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00794&json=true","fetch_graph":"https://pith.science/api/pith-number/CAN62Q3W2DXHVQXRJXAMZGPWD7/graph.json","fetch_events":"https://pith.science/api/pith-number/CAN62Q3W2DXHVQXRJXAMZGPWD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7/action/storage_attestation","attest_author":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7/action/author_attestation","sign_citation":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7/action/citation_signature","submit_replication":"https://pith.science/pith/CAN62Q3W2DXHVQXRJXAMZGPWD7/action/replication_record"}},"created_at":"2026-07-05T09:56:10.337820+00:00","updated_at":"2026-07-05T09:56:10.337820+00:00"}