{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UDOCJB4EIE4OKPR4EQXIJWQNHD","short_pith_number":"pith:UDOCJB4E","schema_version":"1.0","canonical_sha256":"a0dc2487844138e53e3c242e84da0d38e99ff62098d249cfd50da7f8306457bb","source":{"kind":"arxiv","id":"2412.18832","version":1},"attestation_state":"computed","paper":{"title":"Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Guinan Li, Helen Meng, Jiajun Deng, Mengzhe Geng, Mingyu Cui, Shujie Hu, Tianzi Wang, Xunying Liu, Xurong Xie, Zengrui Jin, Zhaoqing Li","submitted_at":"2024-12-25T08:39:02Z","abstract_excerpt":"Data-intensive fine-tuning of speech foundation models (SFMs) to scarce and diverse dysarthric and elderly speech leads to data bias and poor generalization to unseen speakers. This paper proposes novel structured speaker-deficiency adaptation approaches for SSL pre-trained SFMs on such data. Speaker and speech deficiency invariant SFMs were constructed in their supervised adaptive fine-tuning stage to reduce undue bias to training data speakers, and serves as a more neutral and robust starting point for test time unsupervised adaptation. Speech variability attributed to speaker identity and s"},"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":"2412.18832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-25T08:39:02Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"610a055080489925a8b6975e8450bca58faecb65c8a450c36cdad37ec36b7b02","abstract_canon_sha256":"6f5c3b8d50847c73b9e83887b4d3953d6e25ca8446d283c637c3162f587e1522"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:11.580087Z","signature_b64":"ZoIuM/Igv4+nc7k0HnhOwoNH3vnZYTpjfjfaUZXAgxpJ15VznrvkVdPafqq5KMw/5kv/CDATQlyPPk+GhBYdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0dc2487844138e53e3c242e84da0d38e99ff62098d249cfd50da7f8306457bb","last_reissued_at":"2026-07-05T09:54:11.579593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:11.579593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Guinan Li, Helen Meng, Jiajun Deng, Mengzhe Geng, Mingyu Cui, Shujie Hu, Tianzi Wang, Xunying Liu, Xurong Xie, Zengrui Jin, Zhaoqing Li","submitted_at":"2024-12-25T08:39:02Z","abstract_excerpt":"Data-intensive fine-tuning of speech foundation models (SFMs) to scarce and diverse dysarthric and elderly speech leads to data bias and poor generalization to unseen speakers. This paper proposes novel structured speaker-deficiency adaptation approaches for SSL pre-trained SFMs on such data. Speaker and speech deficiency invariant SFMs were constructed in their supervised adaptive fine-tuning stage to reduce undue bias to training data speakers, and serves as a more neutral and robust starting point for test time unsupervised adaptation. Speech variability attributed to speaker identity and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18832","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/2412.18832/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":"2412.18832","created_at":"2026-07-05T09:54:11.579654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18832v1","created_at":"2026-07-05T09:54:11.579654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18832","created_at":"2026-07-05T09:54:11.579654+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDOCJB4EIE4O","created_at":"2026-07-05T09:54:11.579654+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDOCJB4EIE4OKPR4","created_at":"2026-07-05T09:54:11.579654+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDOCJB4E","created_at":"2026-07-05T09:54:11.579654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24224","citing_title":"MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD","json":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD.json","graph_json":"https://pith.science/api/pith-number/UDOCJB4EIE4OKPR4EQXIJWQNHD/graph.json","events_json":"https://pith.science/api/pith-number/UDOCJB4EIE4OKPR4EQXIJWQNHD/events.json","paper":"https://pith.science/paper/UDOCJB4E"},"agent_actions":{"view_html":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD","download_json":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD.json","view_paper":"https://pith.science/paper/UDOCJB4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18832&json=true","fetch_graph":"https://pith.science/api/pith-number/UDOCJB4EIE4OKPR4EQXIJWQNHD/graph.json","fetch_events":"https://pith.science/api/pith-number/UDOCJB4EIE4OKPR4EQXIJWQNHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD/action/storage_attestation","attest_author":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD/action/author_attestation","sign_citation":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD/action/citation_signature","submit_replication":"https://pith.science/pith/UDOCJB4EIE4OKPR4EQXIJWQNHD/action/replication_record"}},"created_at":"2026-07-05T09:54:11.579654+00:00","updated_at":"2026-07-05T09:54:11.579654+00:00"}