{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R6XP4JN6OGSVNWRODEBQYUBPXC","short_pith_number":"pith:R6XP4JN6","schema_version":"1.0","canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","source":{"kind":"arxiv","id":"2501.06478","version":1},"attestation_state":"computed","paper":{"title":"Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Annelien Smith, Christiaan Jacobs, Daleen Klop, Febe de Wet, Herman Kamper, Ond\\v{r}ej Klejch","submitted_at":"2025-01-11T08:11:09Z","abstract_excerpt":"We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of prior child-speech ASR strategies to determine which is best suited to this unique setting. Using Whisper and only 5 minutes of transcribed in-domain child speech, we find that additional in-domain adult data (adult speech matching the story domain) provides the biggest improvement, especially when coupled with voice conversion. Semi-supervised learning also "},"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":"2501.06478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T08:11:09Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"ef4d0c19c48cb45ee77a05e74162244ad3ae533ef00b00ea26e7b06570425047","abstract_canon_sha256":"4ee50354b2ea467b66c4b6a21119f8b19b5a93b98a7894f739be962fb143e016"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:04.072069Z","signature_b64":"jrywIXceDKAKxYq4xmkzc0Xl2R2GVsgiV6EUQtOvdFSnRNpdoXzBbT7+4SRNEIg6Q6fKzYEQ4zeWes/UCP6wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","last_reissued_at":"2026-07-05T10:00:04.071659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:04.071659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Annelien Smith, Christiaan Jacobs, Daleen Klop, Febe de Wet, Herman Kamper, Ond\\v{r}ej Klejch","submitted_at":"2025-01-11T08:11:09Z","abstract_excerpt":"We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of prior child-speech ASR strategies to determine which is best suited to this unique setting. Using Whisper and only 5 minutes of transcribed in-domain child speech, we find that additional in-domain adult data (adult speech matching the story domain) provides the biggest improvement, especially when coupled with voice conversion. Semi-supervised learning also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06478","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/2501.06478/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":"2501.06478","created_at":"2026-07-05T10:00:04.071716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06478v1","created_at":"2026-07-05T10:00:04.071716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06478","created_at":"2026-07-05T10:00:04.071716+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6XP4JN6OGSV","created_at":"2026-07-05T10:00:04.071716+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6XP4JN6OGSVNWRO","created_at":"2026-07-05T10:00:04.071716+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6XP4JN6","created_at":"2026-07-05T10:00:04.071716+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/R6XP4JN6OGSVNWRODEBQYUBPXC","json":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC.json","graph_json":"https://pith.science/api/pith-number/R6XP4JN6OGSVNWRODEBQYUBPXC/graph.json","events_json":"https://pith.science/api/pith-number/R6XP4JN6OGSVNWRODEBQYUBPXC/events.json","paper":"https://pith.science/paper/R6XP4JN6"},"agent_actions":{"view_html":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC","download_json":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC.json","view_paper":"https://pith.science/paper/R6XP4JN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06478&json=true","fetch_graph":"https://pith.science/api/pith-number/R6XP4JN6OGSVNWRODEBQYUBPXC/graph.json","fetch_events":"https://pith.science/api/pith-number/R6XP4JN6OGSVNWRODEBQYUBPXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/action/storage_attestation","attest_author":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/action/author_attestation","sign_citation":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/action/citation_signature","submit_replication":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/action/replication_record"}},"created_at":"2026-07-05T10:00:04.071716+00:00","updated_at":"2026-07-05T10:00:04.071716+00:00"}