{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JJRL4YXH572QIWW7NOKDO2YIJP","short_pith_number":"pith:JJRL4YXH","schema_version":"1.0","canonical_sha256":"4a62be62e7eff5045adf6b94376b084bf558ad3fc664be7ba0d5cd713b60d9c5","source":{"kind":"arxiv","id":"2511.20107","version":1},"attestation_state":"computed","paper":{"title":"Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ha Viet Khanh, Huu Tuong Tu, Nguyen Thi Thu Trang, Nguyen Tien Cuong, Thien Van Luong, Tran Tien Dat, Vu Huan","submitted_at":"2025-11-25T09:26:34Z","abstract_excerpt":"Mispronunciation Detection and Diagnosis (MDD) is crucial for language learning and speech therapy. Unlike conventional methods that require scoring models or training phoneme-level models, we propose a novel training-free framework that leverages retrieval techniques with a pretrained Automatic Speech Recognition model. Our method avoids phoneme-specific modeling or additional task-specific training, while still achieving accurate detection and diagnosis of pronunciation errors. Experiments on the L2-ARCTIC dataset show that our method achieves a superior F1 score of 69.60% while avoiding the"},"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":"2511.20107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-25T09:26:34Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9daf33532617a978578ed394d76d6e6c36253b3c8933d5c8995ca287edaff5ec","abstract_canon_sha256":"39814d112afc224abb6cbb8c603016c08047a219daf9d970293c4574377181b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:31.155434Z","signature_b64":"+aW2gr9tjNOornlt2CZBbdC1LrKfHmaaD+v55iLWcJTGyIColQ2llf7vPDPsdWchPwOH9wtGsMMYsfo2tEndDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a62be62e7eff5045adf6b94376b084bf558ad3fc664be7ba0d5cd713b60d9c5","last_reissued_at":"2026-06-05T01:14:31.154844Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:31.154844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ha Viet Khanh, Huu Tuong Tu, Nguyen Thi Thu Trang, Nguyen Tien Cuong, Thien Van Luong, Tran Tien Dat, Vu Huan","submitted_at":"2025-11-25T09:26:34Z","abstract_excerpt":"Mispronunciation Detection and Diagnosis (MDD) is crucial for language learning and speech therapy. Unlike conventional methods that require scoring models or training phoneme-level models, we propose a novel training-free framework that leverages retrieval techniques with a pretrained Automatic Speech Recognition model. Our method avoids phoneme-specific modeling or additional task-specific training, while still achieving accurate detection and diagnosis of pronunciation errors. Experiments on the L2-ARCTIC dataset show that our method achieves a superior F1 score of 69.60% while avoiding the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20107","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/2511.20107/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":"2511.20107","created_at":"2026-06-05T01:14:31.154911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.20107v1","created_at":"2026-06-05T01:14:31.154911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20107","created_at":"2026-06-05T01:14:31.154911+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJRL4YXH572Q","created_at":"2026-06-05T01:14:31.154911+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJRL4YXH572QIWW7","created_at":"2026-06-05T01:14:31.154911+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJRL4YXH","created_at":"2026-06-05T01:14:31.154911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.22133","citing_title":"Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP","json":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP.json","graph_json":"https://pith.science/api/pith-number/JJRL4YXH572QIWW7NOKDO2YIJP/graph.json","events_json":"https://pith.science/api/pith-number/JJRL4YXH572QIWW7NOKDO2YIJP/events.json","paper":"https://pith.science/paper/JJRL4YXH"},"agent_actions":{"view_html":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP","download_json":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP.json","view_paper":"https://pith.science/paper/JJRL4YXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.20107&json=true","fetch_graph":"https://pith.science/api/pith-number/JJRL4YXH572QIWW7NOKDO2YIJP/graph.json","fetch_events":"https://pith.science/api/pith-number/JJRL4YXH572QIWW7NOKDO2YIJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP/action/storage_attestation","attest_author":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP/action/author_attestation","sign_citation":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP/action/citation_signature","submit_replication":"https://pith.science/pith/JJRL4YXH572QIWW7NOKDO2YIJP/action/replication_record"}},"created_at":"2026-06-05T01:14:31.154911+00:00","updated_at":"2026-06-05T01:14:31.154911+00:00"}