{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C6OQCW7CULBKYT3MDIV5FQADTK","short_pith_number":"pith:C6OQCW7C","schema_version":"1.0","canonical_sha256":"179d015be2a2c2ac4f6c1a2bd2c0039abe7476dc5e42c4eaed8bea154208dd24","source":{"kind":"arxiv","id":"2409.10753","version":2},"attestation_state":"computed","paper":{"title":"Investigating Training Objectives for Generative Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Danilo de Oliveira, Julius Richter, Timo Gerkmann","submitted_at":"2024-09-16T21:47:52Z","abstract_excerpt":"Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims to explain the differences between these frameworks by focusing our investigation on score-based generative models and the Schr\\\"odinger bridge. We conduct a series of comprehensive experiments to compare their performance and highlight differing training behaviors. Furthermore, we propose a novel perceptual loss function tailored for the Schr\\\"od"},"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":"2409.10753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T21:47:52Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"edcc369be4458bb359c9750743a7b12711282dc9268cc877d64becaa3b4f783e","abstract_canon_sha256":"792c8d7c2e3b8464903420d94002003088e37d13b39fa94e2c6f93e38209cfa7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:51.743950Z","signature_b64":"EkoVflOxiSyaSDB8G2PRDAgEUt3goVBfniRWreRTXQgPYfN7QDRJWRUBRArxPTJ84c7IAQtuOqWE68E1CFS6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"179d015be2a2c2ac4f6c1a2bd2c0039abe7476dc5e42c4eaed8bea154208dd24","last_reissued_at":"2026-07-05T10:02:51.743421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:51.743421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Training Objectives for Generative Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Danilo de Oliveira, Julius Richter, Timo Gerkmann","submitted_at":"2024-09-16T21:47:52Z","abstract_excerpt":"Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims to explain the differences between these frameworks by focusing our investigation on score-based generative models and the Schr\\\"odinger bridge. We conduct a series of comprehensive experiments to compare their performance and highlight differing training behaviors. Furthermore, we propose a novel perceptual loss function tailored for the Schr\\\"od"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10753","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/2409.10753/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":"2409.10753","created_at":"2026-07-05T10:02:51.743491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10753v2","created_at":"2026-07-05T10:02:51.743491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10753","created_at":"2026-07-05T10:02:51.743491+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6OQCW7CULBK","created_at":"2026-07-05T10:02:51.743491+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6OQCW7CULBKYT3M","created_at":"2026-07-05T10:02:51.743491+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6OQCW7C","created_at":"2026-07-05T10:02:51.743491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21153","citing_title":"WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK","json":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK.json","graph_json":"https://pith.science/api/pith-number/C6OQCW7CULBKYT3MDIV5FQADTK/graph.json","events_json":"https://pith.science/api/pith-number/C6OQCW7CULBKYT3MDIV5FQADTK/events.json","paper":"https://pith.science/paper/C6OQCW7C"},"agent_actions":{"view_html":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK","download_json":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK.json","view_paper":"https://pith.science/paper/C6OQCW7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10753&json=true","fetch_graph":"https://pith.science/api/pith-number/C6OQCW7CULBKYT3MDIV5FQADTK/graph.json","fetch_events":"https://pith.science/api/pith-number/C6OQCW7CULBKYT3MDIV5FQADTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK/action/storage_attestation","attest_author":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK/action/author_attestation","sign_citation":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK/action/citation_signature","submit_replication":"https://pith.science/pith/C6OQCW7CULBKYT3MDIV5FQADTK/action/replication_record"}},"created_at":"2026-07-05T10:02:51.743491+00:00","updated_at":"2026-07-05T10:02:51.743491+00:00"}