{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WZFBGGSRPHOOHRLLSRSRRUK3R6","short_pith_number":"pith:WZFBGGSR","schema_version":"1.0","canonical_sha256":"b64a131a5179dce3c56b946518d15b8f84a21a42325c6481a6b4ad470d7805c9","source":{"kind":"arxiv","id":"2401.00662","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guinan Li, Haoning Xu, Huimeng Wang, Mengzhe Geng, Shujie Hu, Tianzi Wang, Xunying Liu, Zengrui Jin","submitted_at":"2024-01-01T04:21:19Z","abstract_excerpt":"Automatic recognition of dysarthric speech remains a highly challenging task to date. Neuro-motor conditions and co-occurring physical disabilities create difficulty in large-scale data collection for ASR system development. Adapting SSL pre-trained ASR models to limited dysarthric speech via data-intensive parameter fine-tuning leads to poor generalization. To this end, this paper presents an extensive comparative study of various data augmentation approaches to improve the robustness of pre-trained ASR model fine-tuning to dysarthric speech. These include: a) conventional speaker-independent"},"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":"2401.00662","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-01T04:21:19Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"139c772bbcb3b9bf865246bb8890dd35ccfaa82a86f3515a0ac8dba0b191e32c","abstract_canon_sha256":"d4ffab9adfe1bf0fc50c3872d18c25ef6f6bf2ad261942399fbff3168a90c45c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:21.685673Z","signature_b64":"chnWev97TX7rjm4a0oaplSL61NF/0UcHEAPXzubdU2mR0uKBRzaoTQfbi2gvWD4U+hZtC6Abz8j567j6ST14Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64a131a5179dce3c56b946518d15b8f84a21a42325c6481a6b4ad470d7805c9","last_reissued_at":"2026-07-05T07:29:21.685158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:21.685158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guinan Li, Haoning Xu, Huimeng Wang, Mengzhe Geng, Shujie Hu, Tianzi Wang, Xunying Liu, Zengrui Jin","submitted_at":"2024-01-01T04:21:19Z","abstract_excerpt":"Automatic recognition of dysarthric speech remains a highly challenging task to date. Neuro-motor conditions and co-occurring physical disabilities create difficulty in large-scale data collection for ASR system development. Adapting SSL pre-trained ASR models to limited dysarthric speech via data-intensive parameter fine-tuning leads to poor generalization. To this end, this paper presents an extensive comparative study of various data augmentation approaches to improve the robustness of pre-trained ASR model fine-tuning to dysarthric speech. These include: a) conventional speaker-independent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00662","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/2401.00662/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":"2401.00662","created_at":"2026-07-05T07:29:21.685227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00662v1","created_at":"2026-07-05T07:29:21.685227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00662","created_at":"2026-07-05T07:29:21.685227+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZFBGGSRPHOO","created_at":"2026-07-05T07:29:21.685227+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZFBGGSRPHOOHRLL","created_at":"2026-07-05T07:29:21.685227+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZFBGGSR","created_at":"2026-07-05T07:29:21.685227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31722","citing_title":"Adapting Foundation ASR Models to Dysarthric Speech: A Case Study","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6","json":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6.json","graph_json":"https://pith.science/api/pith-number/WZFBGGSRPHOOHRLLSRSRRUK3R6/graph.json","events_json":"https://pith.science/api/pith-number/WZFBGGSRPHOOHRLLSRSRRUK3R6/events.json","paper":"https://pith.science/paper/WZFBGGSR"},"agent_actions":{"view_html":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6","download_json":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6.json","view_paper":"https://pith.science/paper/WZFBGGSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00662&json=true","fetch_graph":"https://pith.science/api/pith-number/WZFBGGSRPHOOHRLLSRSRRUK3R6/graph.json","fetch_events":"https://pith.science/api/pith-number/WZFBGGSRPHOOHRLLSRSRRUK3R6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6/action/storage_attestation","attest_author":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6/action/author_attestation","sign_citation":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6/action/citation_signature","submit_replication":"https://pith.science/pith/WZFBGGSRPHOOHRLLSRSRRUK3R6/action/replication_record"}},"created_at":"2026-07-05T07:29:21.685227+00:00","updated_at":"2026-07-05T07:29:21.685227+00:00"}