{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UMYDEDNW6C3D5UNJMOGXNEG2VO","short_pith_number":"pith:UMYDEDNW","schema_version":"1.0","canonical_sha256":"a330320db6f0b63ed1a9638d7690daabb06708ac5ffa248d2dd399da07681d36","source":{"kind":"arxiv","id":"2508.08967","version":2},"attestation_state":"computed","paper":{"title":"Revealing the Role of Audio Channels in ASR Performance Degradation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SD","authors_text":"Berlin Chen, Hsin-Min Wang, Hung-Shin Lee, Kuan-Tang Huang, Li-Wei Chen","submitted_at":"2025-08-12T14:32:48Z","abstract_excerpt":"Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the input audio comes from different recording channels. While previous studies have demonstrated this phenomenon, it is often attributed to the mismatch between training and testing corpora. This study argues that variations in speech characteristics caused by different recording channels can fundamentally harm ASR performance. To address this limitation, we propose a normalization technique designed to mitigate the impact "},"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":"2508.08967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-12T14:32:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1422cfe579e8d90875c0f2b0b78092f52fb76cc6f558611af37237193d50a230","abstract_canon_sha256":"0c002a97eb622d56d20054cac6fbfc4a3997a9c59f05814660903a95a22ab842"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:38.702407Z","signature_b64":"NcBrHLMUkttooJYPRYRv62OEdEAseAfux8uwD6Wk8nCo+lU9oEJVZi9x5/IRJqBliUoszJjAIAGZVK8gEDGUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a330320db6f0b63ed1a9638d7690daabb06708ac5ffa248d2dd399da07681d36","last_reissued_at":"2026-07-05T11:57:38.701943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:38.701943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revealing the Role of Audio Channels in ASR Performance Degradation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SD","authors_text":"Berlin Chen, Hsin-Min Wang, Hung-Shin Lee, Kuan-Tang Huang, Li-Wei Chen","submitted_at":"2025-08-12T14:32:48Z","abstract_excerpt":"Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the input audio comes from different recording channels. While previous studies have demonstrated this phenomenon, it is often attributed to the mismatch between training and testing corpora. This study argues that variations in speech characteristics caused by different recording channels can fundamentally harm ASR performance. To address this limitation, we propose a normalization technique designed to mitigate the impact "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08967","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/2508.08967/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":"2508.08967","created_at":"2026-07-05T11:57:38.701991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08967v2","created_at":"2026-07-05T11:57:38.701991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08967","created_at":"2026-07-05T11:57:38.701991+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMYDEDNW6C3D","created_at":"2026-07-05T11:57:38.701991+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMYDEDNW6C3D5UNJ","created_at":"2026-07-05T11:57:38.701991+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMYDEDNW","created_at":"2026-07-05T11:57:38.701991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO","json":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO.json","graph_json":"https://pith.science/api/pith-number/UMYDEDNW6C3D5UNJMOGXNEG2VO/graph.json","events_json":"https://pith.science/api/pith-number/UMYDEDNW6C3D5UNJMOGXNEG2VO/events.json","paper":"https://pith.science/paper/UMYDEDNW"},"agent_actions":{"view_html":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO","download_json":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO.json","view_paper":"https://pith.science/paper/UMYDEDNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08967&json=true","fetch_graph":"https://pith.science/api/pith-number/UMYDEDNW6C3D5UNJMOGXNEG2VO/graph.json","fetch_events":"https://pith.science/api/pith-number/UMYDEDNW6C3D5UNJMOGXNEG2VO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO/action/storage_attestation","attest_author":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO/action/author_attestation","sign_citation":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO/action/citation_signature","submit_replication":"https://pith.science/pith/UMYDEDNW6C3D5UNJMOGXNEG2VO/action/replication_record"}},"created_at":"2026-07-05T11:57:38.701991+00:00","updated_at":"2026-07-05T11:57:38.701991+00:00"}