{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XTMLZI2IKE5NXNWEM2VAEYYYFQ","short_pith_number":"pith:XTMLZI2I","schema_version":"1.0","canonical_sha256":"bcd8bca348513adbb6c466aa0263182c0d5223cc543cd2c0121e5a668e56a27f","source":{"kind":"arxiv","id":"2302.14748","version":2},"attestation_state":"computed","paper":{"title":"Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bunlong Lay, Julius Richter, Simon Welker, Timo Gerkmann","submitted_at":"2023-02-28T16:45:42Z","abstract_excerpt":"Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white Gaussian noise are added to the clean speech signal. While in limit the mean of the forward process ends at the noisy mixture, in practice it stops earlier and thus only at an approximation of the noisy mixture. This results in a discrepancy between the terminating distribution of the forward process and the prior used for solving the reverse process at infe"},"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":"2302.14748","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-02-28T16:45:42Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"031ded3e3528cc3a21a88fc7c4b2670335fb824983512ff6611c66febebaac62","abstract_canon_sha256":"f938ea98157a5363aa4bf54087c26e479a7a2065b16497b484d6e9fde965fa17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:25.269696Z","signature_b64":"SbAf6cI2SF3NpvurBlt8YW5ZWgQdlPyReeASPcrv5gY0svvxj0z4ci53ZJbLeUQ4wC0br3jPSQ8WK5rRNTgLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd8bca348513adbb6c466aa0263182c0d5223cc543cd2c0121e5a668e56a27f","last_reissued_at":"2026-07-05T06:15:25.269287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:25.269287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bunlong Lay, Julius Richter, Simon Welker, Timo Gerkmann","submitted_at":"2023-02-28T16:45:42Z","abstract_excerpt":"Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white Gaussian noise are added to the clean speech signal. While in limit the mean of the forward process ends at the noisy mixture, in practice it stops earlier and thus only at an approximation of the noisy mixture. This results in a discrepancy between the terminating distribution of the forward process and the prior used for solving the reverse process at infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14748","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/2302.14748/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":"2302.14748","created_at":"2026-07-05T06:15:25.269350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14748v2","created_at":"2026-07-05T06:15:25.269350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14748","created_at":"2026-07-05T06:15:25.269350+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTMLZI2IKE5N","created_at":"2026-07-05T06:15:25.269350+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTMLZI2IKE5NXNWE","created_at":"2026-07-05T06:15:25.269350+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTMLZI2I","created_at":"2026-07-05T06:15:25.269350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.21003","citing_title":"Query-Based Asymmetric Modeling with Decoupled Input-Output Rates for Speech Restoration","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ","json":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ.json","graph_json":"https://pith.science/api/pith-number/XTMLZI2IKE5NXNWEM2VAEYYYFQ/graph.json","events_json":"https://pith.science/api/pith-number/XTMLZI2IKE5NXNWEM2VAEYYYFQ/events.json","paper":"https://pith.science/paper/XTMLZI2I"},"agent_actions":{"view_html":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ","download_json":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ.json","view_paper":"https://pith.science/paper/XTMLZI2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14748&json=true","fetch_graph":"https://pith.science/api/pith-number/XTMLZI2IKE5NXNWEM2VAEYYYFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XTMLZI2IKE5NXNWEM2VAEYYYFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ/action/storage_attestation","attest_author":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ/action/author_attestation","sign_citation":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ/action/citation_signature","submit_replication":"https://pith.science/pith/XTMLZI2IKE5NXNWEM2VAEYYYFQ/action/replication_record"}},"created_at":"2026-07-05T06:15:25.269350+00:00","updated_at":"2026-07-05T06:15:25.269350+00:00"}