{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2IVCAYCZW7A2HJ2SHQWJLM5267","short_pith_number":"pith:2IVCAYCZ","schema_version":"1.0","canonical_sha256":"d22a206059b7c1a3a7523c2c95b3baf7d693c7236b811b99447a88d7fa16d219","source":{"kind":"arxiv","id":"2106.03494","version":1},"attestation_state":"computed","paper":{"title":"Weakly-supervised word-level pronunciation error detection in non-native English speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Bozena Kostek, Daniel Korzekwa, Jaime Lorenzo-Trueba, Shira Calamaro, Thomas Drugman","submitted_at":"2021-06-07T10:31:53Z","abstract_excerpt":"We propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced L2 speech, the model is more likely to overfit. To limit this risk, we train it in a multi-task setup. In the first task, we estimate the probabilities of word-leve"},"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":"2106.03494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-07T10:31:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"891ba816b41697b47db679569b2d30c183df302cc05d086bde72f11c69628d4b","abstract_canon_sha256":"c77ddbde0f7ed521a3807811e373430dc256e424b2e7c9f54630dc2b70d1d94a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:50.113371Z","signature_b64":"qeB/Jce+mkddwCf+stlsIs8eWvocn6Tl0OlWD7KhWRuPmc5DAXTnxIamdQmYVfY/GN4Nitt2T29p/jl3aUUrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22a206059b7c1a3a7523c2c95b3baf7d693c7236b811b99447a88d7fa16d219","last_reissued_at":"2026-07-05T02:46:50.112959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:50.112959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly-supervised word-level pronunciation error detection in non-native English speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Bozena Kostek, Daniel Korzekwa, Jaime Lorenzo-Trueba, Shira Calamaro, Thomas Drugman","submitted_at":"2021-06-07T10:31:53Z","abstract_excerpt":"We propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced L2 speech, the model is more likely to overfit. To limit this risk, we train it in a multi-task setup. In the first task, we estimate the probabilities of word-leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03494","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/2106.03494/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":"2106.03494","created_at":"2026-07-05T02:46:50.113017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03494v1","created_at":"2026-07-05T02:46:50.113017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03494","created_at":"2026-07-05T02:46:50.113017+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IVCAYCZW7A2","created_at":"2026-07-05T02:46:50.113017+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IVCAYCZW7A2HJ2S","created_at":"2026-07-05T02:46:50.113017+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IVCAYCZ","created_at":"2026-07-05T02:46:50.113017+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/2IVCAYCZW7A2HJ2SHQWJLM5267","json":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267.json","graph_json":"https://pith.science/api/pith-number/2IVCAYCZW7A2HJ2SHQWJLM5267/graph.json","events_json":"https://pith.science/api/pith-number/2IVCAYCZW7A2HJ2SHQWJLM5267/events.json","paper":"https://pith.science/paper/2IVCAYCZ"},"agent_actions":{"view_html":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267","download_json":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267.json","view_paper":"https://pith.science/paper/2IVCAYCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03494&json=true","fetch_graph":"https://pith.science/api/pith-number/2IVCAYCZW7A2HJ2SHQWJLM5267/graph.json","fetch_events":"https://pith.science/api/pith-number/2IVCAYCZW7A2HJ2SHQWJLM5267/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267/action/storage_attestation","attest_author":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267/action/author_attestation","sign_citation":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267/action/citation_signature","submit_replication":"https://pith.science/pith/2IVCAYCZW7A2HJ2SHQWJLM5267/action/replication_record"}},"created_at":"2026-07-05T02:46:50.113017+00:00","updated_at":"2026-07-05T02:46:50.113017+00:00"}