{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AQPDFIPHC2D4NQNTODGJ5VVVDQ","short_pith_number":"pith:AQPDFIPH","schema_version":"1.0","canonical_sha256":"041e32a1e71687c6c1b370cc9ed6b51c1a4ecc3388f3ebac913c2cfc75d3928c","source":{"kind":"arxiv","id":"2104.01378","version":2},"attestation_state":"computed","paper":{"title":"speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daniel Povey, Junbo Zhang, Ke Li, Qiong Song, Yongqing Wang, Yujun Wang, Yukai Huang, Zhiwen Zhang, Zhiyong Yan","submitted_at":"2021-04-03T11:31:59Z","abstract_excerpt":"This paper introduces a new open-source speech corpus named \"speechocean762\" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children. Five experts annotated each of the utterances at sentence-level, word-level and phoneme-level. A baseline system is released in open source to illustrate the phoneme-level pronunciation assessment workflow on this corpus. This corpus is allowed to be used freely for commercial and non-commercial purposes. It is available for free download from OpenSLR, and the correspo"},"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":"2104.01378","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T11:31:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"79d18c80a7109ff8ef8cbd25db963d2d9c034a1078c8b079382dc9c501d17eb5","abstract_canon_sha256":"58a96e55defd0285461e6f5093199bc148c467ffbc1f4da00b6be5bda36c650c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:37.371362Z","signature_b64":"VI6ORk1c/jorHJJRFtWg1LXmGLhRwFFzzy1wWUuRJZYSlG82RQa/pyJvEhEPPd5nswaV1TNiHRetR9zffG2/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041e32a1e71687c6c1b370cc9ed6b51c1a4ecc3388f3ebac913c2cfc75d3928c","last_reissued_at":"2026-07-05T02:45:37.370678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:37.370678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daniel Povey, Junbo Zhang, Ke Li, Qiong Song, Yongqing Wang, Yujun Wang, Yukai Huang, Zhiwen Zhang, Zhiyong Yan","submitted_at":"2021-04-03T11:31:59Z","abstract_excerpt":"This paper introduces a new open-source speech corpus named \"speechocean762\" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children. Five experts annotated each of the utterances at sentence-level, word-level and phoneme-level. A baseline system is released in open source to illustrate the phoneme-level pronunciation assessment workflow on this corpus. This corpus is allowed to be used freely for commercial and non-commercial purposes. It is available for free download from OpenSLR, and the correspo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01378","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/2104.01378/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":"2104.01378","created_at":"2026-07-05T02:45:37.370753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01378v2","created_at":"2026-07-05T02:45:37.370753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01378","created_at":"2026-07-05T02:45:37.370753+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQPDFIPHC2D4","created_at":"2026-07-05T02:45:37.370753+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQPDFIPHC2D4NQNT","created_at":"2026-07-05T02:45:37.370753+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQPDFIPH","created_at":"2026-07-05T02:45:37.370753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19910","citing_title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ","json":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ.json","graph_json":"https://pith.science/api/pith-number/AQPDFIPHC2D4NQNTODGJ5VVVDQ/graph.json","events_json":"https://pith.science/api/pith-number/AQPDFIPHC2D4NQNTODGJ5VVVDQ/events.json","paper":"https://pith.science/paper/AQPDFIPH"},"agent_actions":{"view_html":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ","download_json":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ.json","view_paper":"https://pith.science/paper/AQPDFIPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01378&json=true","fetch_graph":"https://pith.science/api/pith-number/AQPDFIPHC2D4NQNTODGJ5VVVDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AQPDFIPHC2D4NQNTODGJ5VVVDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ/action/storage_attestation","attest_author":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ/action/author_attestation","sign_citation":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ/action/citation_signature","submit_replication":"https://pith.science/pith/AQPDFIPHC2D4NQNTODGJ5VVVDQ/action/replication_record"}},"created_at":"2026-07-05T02:45:37.370753+00:00","updated_at":"2026-07-05T02:45:37.370753+00:00"}