{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HNPUUZGEZC4M4T6CJXOEZ6JAVF","short_pith_number":"pith:HNPUUZGE","schema_version":"1.0","canonical_sha256":"3b5f4a64c4c8b8ce4fc24ddc4cf920a94e7abc498c42bc218d34f3250adb679c","source":{"kind":"arxiv","id":"2203.17004","version":2},"attestation_state":"computed","paper":{"title":"Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julius Richter, Simon Welker, Timo Gerkmann","submitted_at":"2022-03-31T12:53:47Z","abstract_excerpt":"Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the complex short-time Fourier transform (STFT) domain, proposing a novel training task for speech enhancement using a complex-valued deep neural network. We derive this training task within the formalism of stochastic differential equations (SDEs), thereby enabling the use of predictor-corrector samplers. We provide alternative formulations inspired by previou"},"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":"2203.17004","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-31T12:53:47Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"5d70e21173165c139fa16c9cc0aacd93927cd7a19201e9e5c8ec18d524e5417f","abstract_canon_sha256":"c13af0e91cd9ef8c4ea540d2824494bb59afa3a62c322d62060c74c7561ae5ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:14.392348Z","signature_b64":"VZ1OFBoh6jDyrW5ZFseLIR65LDmAL5qHlBEwc2AsFvHWyVci9qw64IIDFRWzD/n5Wbvj3BEIcKbSyE+sfd4PBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5f4a64c4c8b8ce4fc24ddc4cf920a94e7abc498c42bc218d34f3250adb679c","last_reissued_at":"2026-07-05T04:38:14.391998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:14.391998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julius Richter, Simon Welker, Timo Gerkmann","submitted_at":"2022-03-31T12:53:47Z","abstract_excerpt":"Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the complex short-time Fourier transform (STFT) domain, proposing a novel training task for speech enhancement using a complex-valued deep neural network. We derive this training task within the formalism of stochastic differential equations (SDEs), thereby enabling the use of predictor-corrector samplers. We provide alternative formulations inspired by previou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17004","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/2203.17004/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":"2203.17004","created_at":"2026-07-05T04:38:14.392054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17004v2","created_at":"2026-07-05T04:38:14.392054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17004","created_at":"2026-07-05T04:38:14.392054+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNPUUZGEZC4M","created_at":"2026-07-05T04:38:14.392054+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNPUUZGEZC4M4T6C","created_at":"2026-07-05T04:38:14.392054+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNPUUZGE","created_at":"2026-07-05T04:38:14.392054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10256","citing_title":"A Cold Diffusion Approach for Percussive Dereverberation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF","json":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF.json","graph_json":"https://pith.science/api/pith-number/HNPUUZGEZC4M4T6CJXOEZ6JAVF/graph.json","events_json":"https://pith.science/api/pith-number/HNPUUZGEZC4M4T6CJXOEZ6JAVF/events.json","paper":"https://pith.science/paper/HNPUUZGE"},"agent_actions":{"view_html":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF","download_json":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF.json","view_paper":"https://pith.science/paper/HNPUUZGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17004&json=true","fetch_graph":"https://pith.science/api/pith-number/HNPUUZGEZC4M4T6CJXOEZ6JAVF/graph.json","fetch_events":"https://pith.science/api/pith-number/HNPUUZGEZC4M4T6CJXOEZ6JAVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF/action/storage_attestation","attest_author":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF/action/author_attestation","sign_citation":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF/action/citation_signature","submit_replication":"https://pith.science/pith/HNPUUZGEZC4M4T6CJXOEZ6JAVF/action/replication_record"}},"created_at":"2026-07-05T04:38:14.392054+00:00","updated_at":"2026-07-05T04:38:14.392054+00:00"}