{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EMRX3MTGHSWNOBF6RRDOKZ4NAU","short_pith_number":"pith:EMRX3MTG","schema_version":"1.0","canonical_sha256":"23237db2663cacd704be8c46e5678d05183b2e1d1ef9f8159403f495e95cdc8b","source":{"kind":"arxiv","id":"2212.11851","version":2},"attestation_state":"computed","paper":{"title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann","submitted_at":"2022-12-22T16:35:42Z","abstract_excerpt":"Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing a"},"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":"2212.11851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-12-22T16:35:42Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"6045a9f2a375f59235928bbce2da164353ce109e3df0389e5b928da0394bbf96","abstract_canon_sha256":"15a4d9f93705bb375c6c20d86603c4c69d93a0367cd9ee670bd20c9c0835bfae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:12.477813Z","signature_b64":"ut9bARWW5EwCq11/WS4zd3bBoyzXSkMRdk32E2tAvBBhmDr5Dsl/fPRUnVOQ0TN0OQNrkjqDeNTndVxtHD80DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23237db2663cacd704be8c46e5678d05183b2e1d1ef9f8159403f495e95cdc8b","last_reissued_at":"2026-07-05T07:55:12.477374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:12.477374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann","submitted_at":"2022-12-22T16:35:42Z","abstract_excerpt":"Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11851","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/2212.11851/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":"2212.11851","created_at":"2026-07-05T07:55:12.477431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11851v2","created_at":"2026-07-05T07:55:12.477431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11851","created_at":"2026-07-05T07:55:12.477431+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMRX3MTGHSWN","created_at":"2026-07-05T07:55:12.477431+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMRX3MTGHSWNOBF6","created_at":"2026-07-05T07:55:12.477431+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMRX3MTG","created_at":"2026-07-05T07:55:12.477431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10052","citing_title":"Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU","json":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU.json","graph_json":"https://pith.science/api/pith-number/EMRX3MTGHSWNOBF6RRDOKZ4NAU/graph.json","events_json":"https://pith.science/api/pith-number/EMRX3MTGHSWNOBF6RRDOKZ4NAU/events.json","paper":"https://pith.science/paper/EMRX3MTG"},"agent_actions":{"view_html":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU","download_json":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU.json","view_paper":"https://pith.science/paper/EMRX3MTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11851&json=true","fetch_graph":"https://pith.science/api/pith-number/EMRX3MTGHSWNOBF6RRDOKZ4NAU/graph.json","fetch_events":"https://pith.science/api/pith-number/EMRX3MTGHSWNOBF6RRDOKZ4NAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU/action/storage_attestation","attest_author":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU/action/author_attestation","sign_citation":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU/action/citation_signature","submit_replication":"https://pith.science/pith/EMRX3MTGHSWNOBF6RRDOKZ4NAU/action/replication_record"}},"created_at":"2026-07-05T07:55:12.477431+00:00","updated_at":"2026-07-05T07:55:12.477431+00:00"}