{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S4MVUOLCG7BZL7ZQWI3OL2QUXT","short_pith_number":"pith:S4MVUOLC","schema_version":"1.0","canonical_sha256":"97195a396237c395ff30b236e5ea14bcdf0322ebb52b2b8dbcdc5319de7064a1","source":{"kind":"arxiv","id":"2605.28833","version":1},"attestation_state":"computed","paper":{"title":"Transcribing Children's Speech: ASR Performance and Obtaining Reliable Orthographic Transcriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Catia Cucchiarini, Gus Lathouwers, Helmer Strik, Lingyun Gao","submitted_at":"2026-04-10T13:32:55Z","abstract_excerpt":"Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic transcriptions. However, obtaining reliably high-quality ASR transcriptions for child speech remains challenging in low-resource languages due to limited child-specific pre-trained models and highly diverse noise conditions. This study investigates the effectiveness of state-of-the-art ASR models on child speech through two research questions, by evaluating nine ASR models from three model families (Whisper, Parakeet, and Wav2Vec2) on two Dutch "},"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":"2605.28833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T13:32:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0488c9bf117959a7fb09b99ec8b8d98fa577374f70b943d34fbc03f4ac25c8de","abstract_canon_sha256":"63ffd4d1adcc8070a4fcf6300b567397311de6cef054687738c9547509dd2906"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:13.399146Z","signature_b64":"8wf2O4f1IlAHXIrZaCN0bOByxcea7JCqNq8QBWdDOsQcm19F+TDUJv+XUZt8BNpyxQL3J4s4PyVoz6sxPx6PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97195a396237c395ff30b236e5ea14bcdf0322ebb52b2b8dbcdc5319de7064a1","last_reissued_at":"2026-05-29T00:04:13.398691Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:13.398691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcribing Children's Speech: ASR Performance and Obtaining Reliable Orthographic Transcriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Catia Cucchiarini, Gus Lathouwers, Helmer Strik, Lingyun Gao","submitted_at":"2026-04-10T13:32:55Z","abstract_excerpt":"Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic transcriptions. However, obtaining reliably high-quality ASR transcriptions for child speech remains challenging in low-resource languages due to limited child-specific pre-trained models and highly diverse noise conditions. This study investigates the effectiveness of state-of-the-art ASR models on child speech through two research questions, by evaluating nine ASR models from three model families (Whisper, Parakeet, and Wav2Vec2) on two Dutch "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28833","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/2605.28833/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":"2605.28833","created_at":"2026-05-29T00:04:13.398760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28833v1","created_at":"2026-05-29T00:04:13.398760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28833","created_at":"2026-05-29T00:04:13.398760+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4MVUOLCG7BZ","created_at":"2026-05-29T00:04:13.398760+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4MVUOLCG7BZL7ZQ","created_at":"2026-05-29T00:04:13.398760+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4MVUOLC","created_at":"2026-05-29T00:04:13.398760+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/S4MVUOLCG7BZL7ZQWI3OL2QUXT","json":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT.json","graph_json":"https://pith.science/api/pith-number/S4MVUOLCG7BZL7ZQWI3OL2QUXT/graph.json","events_json":"https://pith.science/api/pith-number/S4MVUOLCG7BZL7ZQWI3OL2QUXT/events.json","paper":"https://pith.science/paper/S4MVUOLC"},"agent_actions":{"view_html":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT","download_json":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT.json","view_paper":"https://pith.science/paper/S4MVUOLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28833&json=true","fetch_graph":"https://pith.science/api/pith-number/S4MVUOLCG7BZL7ZQWI3OL2QUXT/graph.json","fetch_events":"https://pith.science/api/pith-number/S4MVUOLCG7BZL7ZQWI3OL2QUXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT/action/storage_attestation","attest_author":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT/action/author_attestation","sign_citation":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT/action/citation_signature","submit_replication":"https://pith.science/pith/S4MVUOLCG7BZL7ZQWI3OL2QUXT/action/replication_record"}},"created_at":"2026-05-29T00:04:13.398760+00:00","updated_at":"2026-05-29T00:04:13.398760+00:00"}