{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UAWUZVBG5R55WYOEN4ZW5GXVIP","short_pith_number":"pith:UAWUZVBG","schema_version":"1.0","canonical_sha256":"a02d4cd426ec7bdb61c46f336e9af543c4c6716ed7004e275cd6b75f246fd663","source":{"kind":"arxiv","id":"2307.13008","version":1},"attestation_state":"computed","paper":{"title":"Adaptation of Whisper models to child speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Andrei Barcovschi, Horia Cucu, Mariam Yiwere, Peter Corcoran, Rishabh Jain","submitted_at":"2023-07-24T12:54:45Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems often struggle with transcribing child speech due to the lack of large child speech datasets required to accurately train child-friendly ASR models. However, there are huge amounts of annotated adult speech datasets which were used to create multilingual ASR models, such as Whisper. Our work aims to explore whether such models can be adapted to child speech to improve ASR for children. In addition, we compare Whisper child-adaptations with finetuned self-supervised models, such as wav2vec2. We demonstrate that finetuning Whisper on child speech yields"},"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":"2307.13008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-24T12:54:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80466b278d31f6e17da690ba659cb39f3139eb968a121952ddf0749fe748f739","abstract_canon_sha256":"732be76875d9ce805203be39f8f99fc480b5ce034b3df2504c9358c5eb90539c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:07.866722Z","signature_b64":"7TwsgSPdZt4JD+3RYrUt4kX6FilgYNNiQ6tz99nrydKl73l4Pk5DnfJjhADjRRTqUB87RQCUWktiLnWKQdv1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a02d4cd426ec7bdb61c46f336e9af543c4c6716ed7004e275cd6b75f246fd663","last_reissued_at":"2026-07-05T06:34:07.866218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:07.866218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptation of Whisper models to child speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Andrei Barcovschi, Horia Cucu, Mariam Yiwere, Peter Corcoran, Rishabh Jain","submitted_at":"2023-07-24T12:54:45Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems often struggle with transcribing child speech due to the lack of large child speech datasets required to accurately train child-friendly ASR models. However, there are huge amounts of annotated adult speech datasets which were used to create multilingual ASR models, such as Whisper. Our work aims to explore whether such models can be adapted to child speech to improve ASR for children. In addition, we compare Whisper child-adaptations with finetuned self-supervised models, such as wav2vec2. We demonstrate that finetuning Whisper on child speech yields"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13008","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/2307.13008/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":"2307.13008","created_at":"2026-07-05T06:34:07.866291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13008v1","created_at":"2026-07-05T06:34:07.866291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13008","created_at":"2026-07-05T06:34:07.866291+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAWUZVBG5R55","created_at":"2026-07-05T06:34:07.866291+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAWUZVBG5R55WYOE","created_at":"2026-07-05T06:34:07.866291+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAWUZVBG","created_at":"2026-07-05T06:34:07.866291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06439","citing_title":"From Review to Design: Ethical Multimodal Driver Monitoring Systems for Risk Mitigation, Incident Response, and Accountability in Automated Vehicles","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19801","citing_title":"Utterance-Level Methods for Identifying Reliable ASR-Output for Child Speech","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP","json":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP.json","graph_json":"https://pith.science/api/pith-number/UAWUZVBG5R55WYOEN4ZW5GXVIP/graph.json","events_json":"https://pith.science/api/pith-number/UAWUZVBG5R55WYOEN4ZW5GXVIP/events.json","paper":"https://pith.science/paper/UAWUZVBG"},"agent_actions":{"view_html":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP","download_json":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP.json","view_paper":"https://pith.science/paper/UAWUZVBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13008&json=true","fetch_graph":"https://pith.science/api/pith-number/UAWUZVBG5R55WYOEN4ZW5GXVIP/graph.json","fetch_events":"https://pith.science/api/pith-number/UAWUZVBG5R55WYOEN4ZW5GXVIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP/action/storage_attestation","attest_author":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP/action/author_attestation","sign_citation":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP/action/citation_signature","submit_replication":"https://pith.science/pith/UAWUZVBG5R55WYOEN4ZW5GXVIP/action/replication_record"}},"created_at":"2026-07-05T06:34:07.866291+00:00","updated_at":"2026-07-05T06:34:07.866291+00:00"}