{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J77MU4TGY64IHI6IPMBV5O5N25","short_pith_number":"pith:J77MU4TG","schema_version":"1.0","canonical_sha256":"4ffeca7266c7b883a3c87b035ebbadd76755c28ae74fe7c8ae967e111a0c239c","source":{"kind":"arxiv","id":"2311.04936","version":1},"attestation_state":"computed","paper":{"title":"A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrei Barcovschi, Peter Corcoran, Rishabh Jain","submitted_at":"2023-11-07T19:32:48Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems have progressed significantly in their performance on adult speech data; however, transcribing child speech remains challenging due to the acoustic differences in the characteristics of child and adult voices. This work aims to explore the potential of adapting state-of-the-art Conformer-transducer models to child speech to improve child speech recognition performance. Furthermore, the results are compared with those of self-supervised wav2vec2 models and semi-supervised multi-domain Whisper models that were previously finetuned on the same data. We d"},"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":"2311.04936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T19:32:48Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"a70c9fda1c1fbc33435a46ee13c19d62190af63a357cec8765b301f5cccd5c22","abstract_canon_sha256":"794d4f4477182dd2ad47904c901e6dab2b28657f9d62db0a1057afe3d776cd34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:52.196419Z","signature_b64":"muGK/oCyAHm5ZHHmJIHfHxrldNJjuW0LjPbgvDI5lOtPab09cyu+Jd/fDS/8I1wi1z/TjkGcxpBF8kuFAJZWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ffeca7266c7b883a3c87b035ebbadd76755c28ae74fe7c8ae967e111a0c239c","last_reissued_at":"2026-07-05T07:10:52.195954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:52.195954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrei Barcovschi, Peter Corcoran, Rishabh Jain","submitted_at":"2023-11-07T19:32:48Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems have progressed significantly in their performance on adult speech data; however, transcribing child speech remains challenging due to the acoustic differences in the characteristics of child and adult voices. This work aims to explore the potential of adapting state-of-the-art Conformer-transducer models to child speech to improve child speech recognition performance. Furthermore, the results are compared with those of self-supervised wav2vec2 models and semi-supervised multi-domain Whisper models that were previously finetuned on the same data. We d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04936","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/2311.04936/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":"2311.04936","created_at":"2026-07-05T07:10:52.196016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04936v1","created_at":"2026-07-05T07:10:52.196016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04936","created_at":"2026-07-05T07:10:52.196016+00:00"},{"alias_kind":"pith_short_12","alias_value":"J77MU4TGY64I","created_at":"2026-07-05T07:10:52.196016+00:00"},{"alias_kind":"pith_short_16","alias_value":"J77MU4TGY64IHI6I","created_at":"2026-07-05T07:10:52.196016+00:00"},{"alias_kind":"pith_short_8","alias_value":"J77MU4TG","created_at":"2026-07-05T07:10:52.196016+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/J77MU4TGY64IHI6IPMBV5O5N25","json":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25.json","graph_json":"https://pith.science/api/pith-number/J77MU4TGY64IHI6IPMBV5O5N25/graph.json","events_json":"https://pith.science/api/pith-number/J77MU4TGY64IHI6IPMBV5O5N25/events.json","paper":"https://pith.science/paper/J77MU4TG"},"agent_actions":{"view_html":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25","download_json":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25.json","view_paper":"https://pith.science/paper/J77MU4TG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04936&json=true","fetch_graph":"https://pith.science/api/pith-number/J77MU4TGY64IHI6IPMBV5O5N25/graph.json","fetch_events":"https://pith.science/api/pith-number/J77MU4TGY64IHI6IPMBV5O5N25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25/action/storage_attestation","attest_author":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25/action/author_attestation","sign_citation":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25/action/citation_signature","submit_replication":"https://pith.science/pith/J77MU4TGY64IHI6IPMBV5O5N25/action/replication_record"}},"created_at":"2026-07-05T07:10:52.196016+00:00","updated_at":"2026-07-05T07:10:52.196016+00:00"}