{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZOSHNKNF4AEPPZUIT3US7BYZK","short_pith_number":"pith:SZOSHNKN","schema_version":"1.0","canonical_sha256":"965d23b54d2f0047bf3444f7497c38caa328d62ee167295874a4e80c7507603d","source":{"kind":"arxiv","id":"2502.00583","version":1},"attestation_state":"computed","paper":{"title":"Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anna Seo Gyeong Choi, Jonghyeon Park, Myungwoo Oh","submitted_at":"2025-02-01T22:41:43Z","abstract_excerpt":"Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have struggled to fully capture non-native errors. We propose two data-driven approaches using speech corpora to automatically detect mispronunciation patterns. By aligning non-native phones with their native counterparts using attention maps, we achieved a 5.7% improvement in speech recognition on native English datasets and a 12.8% improvement for non-native Engl"},"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":"2502.00583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T22:41:43Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8278c100f9f26a005050e26caeabf5a53d225da6505d41e956e1a17f0c7b86a5","abstract_canon_sha256":"61a4adac8ae9d7180e1f06918022b31392420a77269f53ee3c520137b5fe5699"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:53.317102Z","signature_b64":"K0tj1QDBZKw0Q9DB6uRu70llHTB1gWleXZj8xHcS87AqhMdCEgomRY21NzSDedcBrcrPi7Raqiv36kIlXMpiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"965d23b54d2f0047bf3444f7497c38caa328d62ee167295874a4e80c7507603d","last_reissued_at":"2026-07-05T11:14:53.316673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:53.316673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anna Seo Gyeong Choi, Jonghyeon Park, Myungwoo Oh","submitted_at":"2025-02-01T22:41:43Z","abstract_excerpt":"Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have struggled to fully capture non-native errors. We propose two data-driven approaches using speech corpora to automatically detect mispronunciation patterns. By aligning non-native phones with their native counterparts using attention maps, we achieved a 5.7% improvement in speech recognition on native English datasets and a 12.8% improvement for non-native Engl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00583","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/2502.00583/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":"2502.00583","created_at":"2026-07-05T11:14:53.316732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00583v1","created_at":"2026-07-05T11:14:53.316732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00583","created_at":"2026-07-05T11:14:53.316732+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZOSHNKNF4AE","created_at":"2026-07-05T11:14:53.316732+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZOSHNKNF4AEPPZU","created_at":"2026-07-05T11:14:53.316732+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZOSHNKN","created_at":"2026-07-05T11:14:53.316732+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/SZOSHNKNF4AEPPZUIT3US7BYZK","json":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK.json","graph_json":"https://pith.science/api/pith-number/SZOSHNKNF4AEPPZUIT3US7BYZK/graph.json","events_json":"https://pith.science/api/pith-number/SZOSHNKNF4AEPPZUIT3US7BYZK/events.json","paper":"https://pith.science/paper/SZOSHNKN"},"agent_actions":{"view_html":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK","download_json":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK.json","view_paper":"https://pith.science/paper/SZOSHNKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00583&json=true","fetch_graph":"https://pith.science/api/pith-number/SZOSHNKNF4AEPPZUIT3US7BYZK/graph.json","fetch_events":"https://pith.science/api/pith-number/SZOSHNKNF4AEPPZUIT3US7BYZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK/action/storage_attestation","attest_author":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK/action/author_attestation","sign_citation":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK/action/citation_signature","submit_replication":"https://pith.science/pith/SZOSHNKNF4AEPPZUIT3US7BYZK/action/replication_record"}},"created_at":"2026-07-05T11:14:53.316732+00:00","updated_at":"2026-07-05T11:14:53.316732+00:00"}