{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D26VPJD6JFGBTKLQZPDKY5JSLP","short_pith_number":"pith:D26VPJD6","schema_version":"1.0","canonical_sha256":"1ebd57a47e494c19a970cbc6ac75325bd3bfa07b387546537871e4663ae11a45","source":{"kind":"arxiv","id":"2309.07927","version":3},"attestation_state":"computed","paper":{"title":"Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Adel Attia, Carol Espy-Wilson, Dorottya Demszky, Jing Liu, Wei Ai","submitted_at":"2023-09-12T06:58:18Z","abstract_excerpt":"Recent advancements in Automatic Speech Recognition (ASR) systems, exemplified by Whisper, have demonstrated the potential of these systems to approach human-level performance given sufficient data. However, this progress doesn't readily extend to ASR for children due to the limited availability of suitable child-specific databases and the distinct characteristics of children's speech. A recent study investigated leveraging the My Science Tutor (MyST) children's speech corpus to enhance Whisper's performance in recognizing children's speech. They were able to demonstrate some improvement on a "},"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":"2309.07927","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-12T06:58:18Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"4bc963b94817b6f058051d7c10328ef52715b5ac63277ea98c7794b9286b1e62","abstract_canon_sha256":"49c3b71d9d1a872069f977c508a54c4a3691d17f320de56ba4b2f25bdb06b6af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:20.273694Z","signature_b64":"dhd2T4Ql0KxhHdNM9Ij0mG/lWHRoMRL5P2llUWalMYmi9Wulf+PgY42gllM5rz/E/HEq/c8P6UCvosE7mWkTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ebd57a47e494c19a970cbc6ac75325bd3bfa07b387546537871e4663ae11a45","last_reissued_at":"2026-07-05T08:19:20.273245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:20.273245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Adel Attia, Carol Espy-Wilson, Dorottya Demszky, Jing Liu, Wei Ai","submitted_at":"2023-09-12T06:58:18Z","abstract_excerpt":"Recent advancements in Automatic Speech Recognition (ASR) systems, exemplified by Whisper, have demonstrated the potential of these systems to approach human-level performance given sufficient data. However, this progress doesn't readily extend to ASR for children due to the limited availability of suitable child-specific databases and the distinct characteristics of children's speech. A recent study investigated leveraging the My Science Tutor (MyST) children's speech corpus to enhance Whisper's performance in recognizing children's speech. They were able to demonstrate some improvement on a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07927","kind":"arxiv","version":3},"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/2309.07927/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":"2309.07927","created_at":"2026-07-05T08:19:20.273305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07927v3","created_at":"2026-07-05T08:19:20.273305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07927","created_at":"2026-07-05T08:19:20.273305+00:00"},{"alias_kind":"pith_short_12","alias_value":"D26VPJD6JFGB","created_at":"2026-07-05T08:19:20.273305+00:00"},{"alias_kind":"pith_short_16","alias_value":"D26VPJD6JFGBTKLQ","created_at":"2026-07-05T08:19:20.273305+00:00"},{"alias_kind":"pith_short_8","alias_value":"D26VPJD6","created_at":"2026-07-05T08:19:20.273305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09206","citing_title":"SimClass: A Classroom Speech Dataset Generated via Game Engine Simulation For Automatic Speech Recognition Research","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP","json":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP.json","graph_json":"https://pith.science/api/pith-number/D26VPJD6JFGBTKLQZPDKY5JSLP/graph.json","events_json":"https://pith.science/api/pith-number/D26VPJD6JFGBTKLQZPDKY5JSLP/events.json","paper":"https://pith.science/paper/D26VPJD6"},"agent_actions":{"view_html":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP","download_json":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP.json","view_paper":"https://pith.science/paper/D26VPJD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07927&json=true","fetch_graph":"https://pith.science/api/pith-number/D26VPJD6JFGBTKLQZPDKY5JSLP/graph.json","fetch_events":"https://pith.science/api/pith-number/D26VPJD6JFGBTKLQZPDKY5JSLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP/action/storage_attestation","attest_author":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP/action/author_attestation","sign_citation":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP/action/citation_signature","submit_replication":"https://pith.science/pith/D26VPJD6JFGBTKLQZPDKY5JSLP/action/replication_record"}},"created_at":"2026-07-05T08:19:20.273305+00:00","updated_at":"2026-07-05T08:19:20.273305+00:00"}