{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NOMHZ2YDEK3BC7OY3SUQSYJ2CB","short_pith_number":"pith:NOMHZ2YD","schema_version":"1.0","canonical_sha256":"6b987ceb0322b6117dd8dca909613a1040efc6a4f045c0c85373dbd39623b22c","source":{"kind":"arxiv","id":"2407.04280","version":2},"attestation_state":"computed","paper":{"title":"LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongyeop Kang, Haechan Kim, Juho Kim, Junho Myung, Seoyoung Kim, Sungpah Lee","submitted_at":"2024-07-05T06:25:54Z","abstract_excerpt":"Prevalent ungrammatical expressions and disfluencies in spontaneous speech from second language (L2) learners pose unique challenges to Automatic Speech Recognition (ASR) systems. However, few datasets are tailored to L2 learner speech. We publicly release LearnerVoice, a dataset consisting of 50.04 hours of audio and transcriptions of L2 learners' spontaneous speech. Our linguistic analysis reveals that transcriptions in our dataset contain L2S (L2 learner's Spontaneous speech) features, consisting of ungrammatical expressions and disfluencies (e.g., filler words, word repetitions, self-repai"},"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":"2407.04280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T06:25:54Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3f061fc87b939b06d4b7e66b804c578b369923a639b3da28da0d42cad8a1631f","abstract_canon_sha256":"769d8bc90919ce8c1bc047a8b7898066c4bcdb97b1c4d55e6720ca970cfb89f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:34.749291Z","signature_b64":"hE5HGhzAqUQe3CbVTUNCixYhK1BOUosxBIrBFvWCWQiRfe3y8OERf+qOGoFBKUcyWDL0F343BMXkP8O61EvLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b987ceb0322b6117dd8dca909613a1040efc6a4f045c0c85373dbd39623b22c","last_reissued_at":"2026-07-05T09:15:34.748735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:34.748735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongyeop Kang, Haechan Kim, Juho Kim, Junho Myung, Seoyoung Kim, Sungpah Lee","submitted_at":"2024-07-05T06:25:54Z","abstract_excerpt":"Prevalent ungrammatical expressions and disfluencies in spontaneous speech from second language (L2) learners pose unique challenges to Automatic Speech Recognition (ASR) systems. However, few datasets are tailored to L2 learner speech. We publicly release LearnerVoice, a dataset consisting of 50.04 hours of audio and transcriptions of L2 learners' spontaneous speech. Our linguistic analysis reveals that transcriptions in our dataset contain L2S (L2 learner's Spontaneous speech) features, consisting of ungrammatical expressions and disfluencies (e.g., filler words, word repetitions, self-repai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04280","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/2407.04280/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":"2407.04280","created_at":"2026-07-05T09:15:34.748795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04280v2","created_at":"2026-07-05T09:15:34.748795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04280","created_at":"2026-07-05T09:15:34.748795+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOMHZ2YDEK3B","created_at":"2026-07-05T09:15:34.748795+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOMHZ2YDEK3BC7OY","created_at":"2026-07-05T09:15:34.748795+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOMHZ2YD","created_at":"2026-07-05T09:15:34.748795+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/NOMHZ2YDEK3BC7OY3SUQSYJ2CB","json":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB.json","graph_json":"https://pith.science/api/pith-number/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/graph.json","events_json":"https://pith.science/api/pith-number/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/events.json","paper":"https://pith.science/paper/NOMHZ2YD"},"agent_actions":{"view_html":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB","download_json":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB.json","view_paper":"https://pith.science/paper/NOMHZ2YD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04280&json=true","fetch_graph":"https://pith.science/api/pith-number/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/graph.json","fetch_events":"https://pith.science/api/pith-number/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/action/storage_attestation","attest_author":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/action/author_attestation","sign_citation":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/action/citation_signature","submit_replication":"https://pith.science/pith/NOMHZ2YDEK3BC7OY3SUQSYJ2CB/action/replication_record"}},"created_at":"2026-07-05T09:15:34.748795+00:00","updated_at":"2026-07-05T09:15:34.748795+00:00"}