{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P4EYEEYSV44YTJUDI3BE4WIFNK","short_pith_number":"pith:P4EYEEYS","schema_version":"1.0","canonical_sha256":"7f09821312af3989a68346c24e59056a9c2b78cfdea537ec2ab834f8200d98ee","source":{"kind":"arxiv","id":"2606.19823","version":1},"attestation_state":"computed","paper":{"title":"Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Clarion Mendes, Hasegawa-Johnson, Qianli Wang, Satwinder Singh, Seyed Reza Shahamiri, Waleed Abdulla, Zihan Zhong","submitted_at":"2026-06-18T05:55:58Z","abstract_excerpt":"Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability. While synthetic data can address these gaps, traditional methods often require extensive speaker-specific data, reintroducing the collection bottleneck. We investigate zero-shot voice cloning as a low-burden augmentation strategy, using Higgs Audio V2 to clone speakers in the TORGO dataset. We fine-tune (FT) Whisper-medium on cloned, real, and hybrid data and evaluate on held-out real speech. Compared to the zero-shot (31.62%), Clone FT achieved a competitive 26.00% WE"},"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":"2606.19823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T05:55:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53767ff50db16657762b1d52dc7645680a02ca9b7d0caac29edf42c10d134683","abstract_canon_sha256":"eb4c4c1b7af653add5447c39f4a37c394c18f1ca531fa22cf5f318d9565d8a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:36.261375Z","signature_b64":"iP8TRGUMe+nmOAUwtJMFaYyFDPhmkWgKDicX/1vP7DgonuJyxQRPjR3LtEBV07jyljqXENNbKDfJIO9T47f6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f09821312af3989a68346c24e59056a9c2b78cfdea537ec2ab834f8200d98ee","last_reissued_at":"2026-06-19T16:12:36.261021Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:36.261021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Clarion Mendes, Hasegawa-Johnson, Qianli Wang, Satwinder Singh, Seyed Reza Shahamiri, Waleed Abdulla, Zihan Zhong","submitted_at":"2026-06-18T05:55:58Z","abstract_excerpt":"Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability. While synthetic data can address these gaps, traditional methods often require extensive speaker-specific data, reintroducing the collection bottleneck. We investigate zero-shot voice cloning as a low-burden augmentation strategy, using Higgs Audio V2 to clone speakers in the TORGO dataset. We fine-tune (FT) Whisper-medium on cloned, real, and hybrid data and evaluate on held-out real speech. Compared to the zero-shot (31.62%), Clone FT achieved a competitive 26.00% WE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19823","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/2606.19823/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":"2606.19823","created_at":"2026-06-19T16:12:36.261082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19823v1","created_at":"2026-06-19T16:12:36.261082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19823","created_at":"2026-06-19T16:12:36.261082+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4EYEEYSV44Y","created_at":"2026-06-19T16:12:36.261082+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4EYEEYSV44YTJUD","created_at":"2026-06-19T16:12:36.261082+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4EYEEYS","created_at":"2026-06-19T16:12:36.261082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.19823","citing_title":"Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK","json":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK.json","graph_json":"https://pith.science/api/pith-number/P4EYEEYSV44YTJUDI3BE4WIFNK/graph.json","events_json":"https://pith.science/api/pith-number/P4EYEEYSV44YTJUDI3BE4WIFNK/events.json","paper":"https://pith.science/paper/P4EYEEYS"},"agent_actions":{"view_html":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK","download_json":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK.json","view_paper":"https://pith.science/paper/P4EYEEYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19823&json=true","fetch_graph":"https://pith.science/api/pith-number/P4EYEEYSV44YTJUDI3BE4WIFNK/graph.json","fetch_events":"https://pith.science/api/pith-number/P4EYEEYSV44YTJUDI3BE4WIFNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK/action/storage_attestation","attest_author":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK/action/author_attestation","sign_citation":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK/action/citation_signature","submit_replication":"https://pith.science/pith/P4EYEEYSV44YTJUDI3BE4WIFNK/action/replication_record"}},"created_at":"2026-06-19T16:12:36.261082+00:00","updated_at":"2026-06-19T16:12:36.261082+00:00"}