{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZIEA5EICKT4NDNVVRVOQOIQB6D","short_pith_number":"pith:ZIEA5EIC","schema_version":"1.0","canonical_sha256":"ca080e910254f8d1b6b58d5d072201f0ecfe1967f409d5a678f93a4be758d5d8","source":{"kind":"arxiv","id":"2502.07029","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Mortensen, Eunjung Yeo, Kalvin Chang, Kwanghee Choi, Shinji Watanabe","submitted_at":"2025-02-10T20:46:42Z","abstract_excerpt":"Allophony refers to the variation in the phonetic realization of a phoneme based on its phonetic environment. Modeling allophones is crucial for atypical pronunciation assessment, which involves distinguishing atypical from typical pronunciations. However, recent phoneme classifier-based approaches often simplify this by treating various realizations as a single phoneme, bypassing the complexity of modeling allophonic variation. Motivated by the acoustic modeling capabilities of frozen self-supervised speech model (S3M) features, we propose MixGoP, a novel approach that leverages Gaussian mixt"},"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":"2502.07029","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T20:46:42Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"459e0e7f08cccdf861775873d13af603fd574750d0b7b5bfb396032bd97bc785","abstract_canon_sha256":"b9acd8219503c5b33c69e632d5ac8cdfa99a6ed33ff3692e73bb73d480444988"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:44.512287Z","signature_b64":"UwKuxCLgDSGkH3Fio6IUjggEinzHDJjFdEdKWOnARsnzzyvU+wVp5wcVYypuddKFwn3VRuTqPcTqm+WpXWCbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca080e910254f8d1b6b58d5d072201f0ecfe1967f409d5a678f93a4be758d5d8","last_reissued_at":"2026-07-05T10:37:44.511747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:44.511747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Mortensen, Eunjung Yeo, Kalvin Chang, Kwanghee Choi, Shinji Watanabe","submitted_at":"2025-02-10T20:46:42Z","abstract_excerpt":"Allophony refers to the variation in the phonetic realization of a phoneme based on its phonetic environment. Modeling allophones is crucial for atypical pronunciation assessment, which involves distinguishing atypical from typical pronunciations. However, recent phoneme classifier-based approaches often simplify this by treating various realizations as a single phoneme, bypassing the complexity of modeling allophonic variation. Motivated by the acoustic modeling capabilities of frozen self-supervised speech model (S3M) features, we propose MixGoP, a novel approach that leverages Gaussian mixt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07029","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/2502.07029/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":"2502.07029","created_at":"2026-07-05T10:37:44.511803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07029v2","created_at":"2026-07-05T10:37:44.511803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07029","created_at":"2026-07-05T10:37:44.511803+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIEA5EICKT4N","created_at":"2026-07-05T10:37:44.511803+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIEA5EICKT4NDNVV","created_at":"2026-07-05T10:37:44.511803+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIEA5EIC","created_at":"2026-07-05T10:37:44.511803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00454","citing_title":"Towards Temporally Explainable Dysarthric Speech Clarity Assessment","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D","json":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D.json","graph_json":"https://pith.science/api/pith-number/ZIEA5EICKT4NDNVVRVOQOIQB6D/graph.json","events_json":"https://pith.science/api/pith-number/ZIEA5EICKT4NDNVVRVOQOIQB6D/events.json","paper":"https://pith.science/paper/ZIEA5EIC"},"agent_actions":{"view_html":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D","download_json":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D.json","view_paper":"https://pith.science/paper/ZIEA5EIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07029&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIEA5EICKT4NDNVVRVOQOIQB6D/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIEA5EICKT4NDNVVRVOQOIQB6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D/action/storage_attestation","attest_author":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D/action/author_attestation","sign_citation":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D/action/citation_signature","submit_replication":"https://pith.science/pith/ZIEA5EICKT4NDNVVRVOQOIQB6D/action/replication_record"}},"created_at":"2026-07-05T10:37:44.511803+00:00","updated_at":"2026-07-05T10:37:44.511803+00:00"}