{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKGOWSGIWPPBWI7XEPDMFMVEYV","short_pith_number":"pith:QKGOWSGI","schema_version":"1.0","canonical_sha256":"828ceb48c8b3de1b23f723c6c2b2a4c556c9f7af397ca08550f817c172e64f99","source":{"kind":"arxiv","id":"2404.14860","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hiroshi Sato, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Shigeru Katagiri, Shoko Araki, Tsubasa Ochiai","submitted_at":"2024-04-23T09:30:23Z","abstract_excerpt":"It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with a single-channel speech enhancement (SE) front-end. This is generally attributed to the processing distortions caused by the nonlinear processing of single-channel SE front-ends. However, the causes of such degraded ASR performance have not been fully investigated. How to design single-channel SE front-ends in a way that significantly improves ASR performance remains an open research question. In this study, we investigate a signal-level numerical metric that can explain the cause of degradatio"},"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":"2404.14860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-23T09:30:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a887b7a0dcad85111cc06892bcd0f7586f1f3f3e6482e4867be7b457f8f20f33","abstract_canon_sha256":"c517417514cadc2e9513f4e76ae0e58dd158235d41715c86be9a75b1b28773bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:11.192994Z","signature_b64":"5vgXqyL8qKqV5gGgCnIFh0TynxO9gRa9yoea2/Zn69LVmtIADP2AnmQaP4JTdERNLLLBBuZ6KOpD0bOB3V6eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"828ceb48c8b3de1b23f723c6c2b2a4c556c9f7af397ca08550f817c172e64f99","last_reissued_at":"2026-07-05T08:11:11.192575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:11.192575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hiroshi Sato, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Shigeru Katagiri, Shoko Araki, Tsubasa Ochiai","submitted_at":"2024-04-23T09:30:23Z","abstract_excerpt":"It is challenging to improve automatic speech recognition (ASR) performance in noisy conditions with a single-channel speech enhancement (SE) front-end. This is generally attributed to the processing distortions caused by the nonlinear processing of single-channel SE front-ends. However, the causes of such degraded ASR performance have not been fully investigated. How to design single-channel SE front-ends in a way that significantly improves ASR performance remains an open research question. In this study, we investigate a signal-level numerical metric that can explain the cause of degradatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14860","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/2404.14860/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":"2404.14860","created_at":"2026-07-05T08:11:11.192630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14860v1","created_at":"2026-07-05T08:11:11.192630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14860","created_at":"2026-07-05T08:11:11.192630+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKGOWSGIWPPB","created_at":"2026-07-05T08:11:11.192630+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKGOWSGIWPPBWI7X","created_at":"2026-07-05T08:11:11.192630+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKGOWSGI","created_at":"2026-07-05T08:11:11.192630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07631","citing_title":"Generic Speech Enhancement with Self-Supervised Representation Space Loss","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV","json":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV.json","graph_json":"https://pith.science/api/pith-number/QKGOWSGIWPPBWI7XEPDMFMVEYV/graph.json","events_json":"https://pith.science/api/pith-number/QKGOWSGIWPPBWI7XEPDMFMVEYV/events.json","paper":"https://pith.science/paper/QKGOWSGI"},"agent_actions":{"view_html":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV","download_json":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV.json","view_paper":"https://pith.science/paper/QKGOWSGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14860&json=true","fetch_graph":"https://pith.science/api/pith-number/QKGOWSGIWPPBWI7XEPDMFMVEYV/graph.json","fetch_events":"https://pith.science/api/pith-number/QKGOWSGIWPPBWI7XEPDMFMVEYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV/action/storage_attestation","attest_author":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV/action/author_attestation","sign_citation":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV/action/citation_signature","submit_replication":"https://pith.science/pith/QKGOWSGIWPPBWI7XEPDMFMVEYV/action/replication_record"}},"created_at":"2026-07-05T08:11:11.192630+00:00","updated_at":"2026-07-05T08:11:11.192630+00:00"}