{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ","short_pith_number":"pith:Q7ZQ4UID","schema_version":"1.0","canonical_sha256":"87f30e510398662b40cf262fd219f8be4d114e0bbaf1959864ec02417df89cee","source":{"kind":"arxiv","id":"2407.06310","version":1},"attestation_state":"computed","paper":{"title":"Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guinan Li, Helen Meng, Jiajun Deng, Mengzhe Geng, Shujie Hu, Tianzi Wang, Xunying Liu, Xurong Xie, Zengrui Jin, Zhaoqing Li","submitted_at":"2024-07-08T18:20:24Z","abstract_excerpt":"The application of data-intensive automatic speech recognition (ASR) technologies to dysarthric and elderly adult speech is confronted by their mismatch against healthy and nonaged voices, data scarcity and large speaker-level variability. To this end, this paper proposes two novel data-efficient methods to learn homogeneous dysarthric and elderly speaker-level features for rapid, on-the-fly test-time adaptation of DNN/TDNN and Conformer ASR models. These include: 1) speaker-level variance-regularized spectral basis embedding (VR-SBE) features that exploit a special regularization term to enfo"},"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":"2407.06310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-08T18:20:24Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","eess.AS"],"title_canon_sha256":"deeaf62b8fc8f6fffa47666fcfbd2df63cf04586efc48d715fb6884fbbcc4135","abstract_canon_sha256":"b1508df46afec8ca7717a6239046140feef4a908e131d31239305a804cf14ca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:28.599268Z","signature_b64":"VRb97inWJ5wz1txaxlFz6IYyj2SX74o2P2XNmvV1r8MoQOnK8559DpvoWu3yKgWFGE45fNZe7+SYfqve862xBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87f30e510398662b40cf262fd219f8be4d114e0bbaf1959864ec02417df89cee","last_reissued_at":"2026-07-05T08:41:28.598784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:28.598784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guinan Li, Helen Meng, Jiajun Deng, Mengzhe Geng, Shujie Hu, Tianzi Wang, Xunying Liu, Xurong Xie, Zengrui Jin, Zhaoqing Li","submitted_at":"2024-07-08T18:20:24Z","abstract_excerpt":"The application of data-intensive automatic speech recognition (ASR) technologies to dysarthric and elderly adult speech is confronted by their mismatch against healthy and nonaged voices, data scarcity and large speaker-level variability. To this end, this paper proposes two novel data-efficient methods to learn homogeneous dysarthric and elderly speaker-level features for rapid, on-the-fly test-time adaptation of DNN/TDNN and Conformer ASR models. These include: 1) speaker-level variance-regularized spectral basis embedding (VR-SBE) features that exploit a special regularization term to enfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06310","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/2407.06310/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":"2407.06310","created_at":"2026-07-05T08:41:28.598846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06310v1","created_at":"2026-07-05T08:41:28.598846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06310","created_at":"2026-07-05T08:41:28.598846+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7ZQ4UIDTBTC","created_at":"2026-07-05T08:41:28.598846+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7ZQ4UIDTBTCWQGP","created_at":"2026-07-05T08:41:28.598846+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7ZQ4UID","created_at":"2026-07-05T08:41:28.598846+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":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ","json":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ.json","graph_json":"https://pith.science/api/pith-number/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/graph.json","events_json":"https://pith.science/api/pith-number/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/events.json","paper":"https://pith.science/paper/Q7ZQ4UID"},"agent_actions":{"view_html":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ","download_json":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ.json","view_paper":"https://pith.science/paper/Q7ZQ4UID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06310&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/action/storage_attestation","attest_author":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/action/author_attestation","sign_citation":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/action/citation_signature","submit_replication":"https://pith.science/pith/Q7ZQ4UIDTBTCWQGPEYX5EGPYXZ/action/replication_record"}},"created_at":"2026-07-05T08:41:28.598846+00:00","updated_at":"2026-07-05T08:41:28.598846+00:00"}