{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KLZKIOXSVVNJFCOHWU2C5AVULD","short_pith_number":"pith:KLZKIOXS","schema_version":"1.0","canonical_sha256":"52f2a43af2ad5a9289c7b5342e82b458ce3b96aca24db0fd4c9c88025b638d27","source":{"kind":"arxiv","id":"2203.11562","version":2},"attestation_state":"computed","paper":{"title":"A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dan Bigioi, Horia Cucu, Mariam Yiwere, Peter Corcoran, Rishabh Jain","submitted_at":"2022-03-22T09:34:21Z","abstract_excerpt":"Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech. However, most of the TTS research focuses on using adult speech data and there has been very limited work done on child speech synthesis. This study developed and validated a training pipeline for fine-tuning state-of-the-art (SOTA) neural TTS models using child speech datasets. This approach adopts a multi-speaker TTS retuning workflow to provide a transfer-learning pipeline. A publicly available child speech dataset was cleaned to provide a smaller subset of approximate"},"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":"2203.11562","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-22T09:34:21Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"2dd94bb488938b2f2db147a6c91fb7ff7765be0d837544b33681b79533b43c5f","abstract_canon_sha256":"c2584b3ce78eace73df1cebf7d954af2fa7e9f7092ebbe9c1508da788a7f2485"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:12.756919Z","signature_b64":"hPbV+8y5Zh5/9hgV5l794fUsDD3nWYsqTtPJZLcQ/CNWzqjQTzcXes/esc+mrXpfAu2+Y1rTOVnRNBWttfJSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f2a43af2ad5a9289c7b5342e82b458ce3b96aca24db0fd4c9c88025b638d27","last_reissued_at":"2026-07-05T04:11:12.756476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:12.756476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dan Bigioi, Horia Cucu, Mariam Yiwere, Peter Corcoran, Rishabh Jain","submitted_at":"2022-03-22T09:34:21Z","abstract_excerpt":"Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech. However, most of the TTS research focuses on using adult speech data and there has been very limited work done on child speech synthesis. This study developed and validated a training pipeline for fine-tuning state-of-the-art (SOTA) neural TTS models using child speech datasets. This approach adopts a multi-speaker TTS retuning workflow to provide a transfer-learning pipeline. A publicly available child speech dataset was cleaned to provide a smaller subset of approximate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11562","kind":"arxiv","version":2},"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/2203.11562/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":"2203.11562","created_at":"2026-07-05T04:11:12.756533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11562v2","created_at":"2026-07-05T04:11:12.756533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11562","created_at":"2026-07-05T04:11:12.756533+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLZKIOXSVVNJ","created_at":"2026-07-05T04:11:12.756533+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLZKIOXSVVNJFCOH","created_at":"2026-07-05T04:11:12.756533+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLZKIOXS","created_at":"2026-07-05T04:11:12.756533+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/KLZKIOXSVVNJFCOHWU2C5AVULD","json":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD.json","graph_json":"https://pith.science/api/pith-number/KLZKIOXSVVNJFCOHWU2C5AVULD/graph.json","events_json":"https://pith.science/api/pith-number/KLZKIOXSVVNJFCOHWU2C5AVULD/events.json","paper":"https://pith.science/paper/KLZKIOXS"},"agent_actions":{"view_html":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD","download_json":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD.json","view_paper":"https://pith.science/paper/KLZKIOXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11562&json=true","fetch_graph":"https://pith.science/api/pith-number/KLZKIOXSVVNJFCOHWU2C5AVULD/graph.json","fetch_events":"https://pith.science/api/pith-number/KLZKIOXSVVNJFCOHWU2C5AVULD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD/action/storage_attestation","attest_author":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD/action/author_attestation","sign_citation":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD/action/citation_signature","submit_replication":"https://pith.science/pith/KLZKIOXSVVNJFCOHWU2C5AVULD/action/replication_record"}},"created_at":"2026-07-05T04:11:12.756533+00:00","updated_at":"2026-07-05T04:11:12.756533+00:00"}