{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HBY5VAVVUCHUWBMYAUHATLSAQA","short_pith_number":"pith:HBY5VAVV","schema_version":"1.0","canonical_sha256":"3871da82b5a08f4b0598050e09ae408028126a6613360ab12fd9a5f4e0e4bb0c","source":{"kind":"arxiv","id":"2505.22072","version":1},"attestation_state":"computed","paper":{"title":"On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chengxi Deng, Guinan Li, Helen Meng, Huimeng Wang, Jiajun Deng, Mengzhe Geng, Mingyu Cui, Shujie Hu, Tianzi Wang, Xunying Liu, Xurong Xie","submitted_at":"2025-05-28T07:52:58Z","abstract_excerpt":"This paper proposes a novel MoE-based speaker adaptation framework for foundation models based dysarthric speech recognition. This approach enables zero-shot adaptation and real-time processing while incorporating domain knowledge. Speech impairment severity and gender conditioned adapter experts are dynamically combined using on-the-fly predicted speaker-dependent routing parameters. KL-divergence is used to further enforce diversity among experts and their generalization to unseen speakers. Experimental results on the UASpeech corpus suggest that on-the-fly MoE-based adaptation produces stat"},"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":"2505.22072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:52:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9665070bbd73605ffbd1de862013fd861664d48890d93a72b616a11cc231f2c1","abstract_canon_sha256":"e55fb55e5c4fc3ef1c4be9fe6c18dc3cbace8b0a7a59cf38306b3d735372bb40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:09.322263Z","signature_b64":"HGEjfdyZmJS0oh0KA5a0Lj4SDrekQJuxS+LONu+XJGpGFadyuPwcgtPSVDe7Cq9jm1odBYxiJTD1ZkHxcZOLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3871da82b5a08f4b0598050e09ae408028126a6613360ab12fd9a5f4e0e4bb0c","last_reissued_at":"2026-07-05T11:11:09.321698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:09.321698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chengxi Deng, Guinan Li, Helen Meng, Huimeng Wang, Jiajun Deng, Mengzhe Geng, Mingyu Cui, Shujie Hu, Tianzi Wang, Xunying Liu, Xurong Xie","submitted_at":"2025-05-28T07:52:58Z","abstract_excerpt":"This paper proposes a novel MoE-based speaker adaptation framework for foundation models based dysarthric speech recognition. This approach enables zero-shot adaptation and real-time processing while incorporating domain knowledge. Speech impairment severity and gender conditioned adapter experts are dynamically combined using on-the-fly predicted speaker-dependent routing parameters. KL-divergence is used to further enforce diversity among experts and their generalization to unseen speakers. Experimental results on the UASpeech corpus suggest that on-the-fly MoE-based adaptation produces stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22072","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/2505.22072/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":"2505.22072","created_at":"2026-07-05T11:11:09.321763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22072v1","created_at":"2026-07-05T11:11:09.321763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22072","created_at":"2026-07-05T11:11:09.321763+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBY5VAVVUCHU","created_at":"2026-07-05T11:11:09.321763+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBY5VAVVUCHUWBMY","created_at":"2026-07-05T11:11:09.321763+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBY5VAVV","created_at":"2026-07-05T11:11:09.321763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22072","citing_title":"On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA","json":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA.json","graph_json":"https://pith.science/api/pith-number/HBY5VAVVUCHUWBMYAUHATLSAQA/graph.json","events_json":"https://pith.science/api/pith-number/HBY5VAVVUCHUWBMYAUHATLSAQA/events.json","paper":"https://pith.science/paper/HBY5VAVV"},"agent_actions":{"view_html":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA","download_json":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA.json","view_paper":"https://pith.science/paper/HBY5VAVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22072&json=true","fetch_graph":"https://pith.science/api/pith-number/HBY5VAVVUCHUWBMYAUHATLSAQA/graph.json","fetch_events":"https://pith.science/api/pith-number/HBY5VAVVUCHUWBMYAUHATLSAQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA/action/storage_attestation","attest_author":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA/action/author_attestation","sign_citation":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA/action/citation_signature","submit_replication":"https://pith.science/pith/HBY5VAVVUCHUWBMYAUHATLSAQA/action/replication_record"}},"created_at":"2026-07-05T11:11:09.321763+00:00","updated_at":"2026-07-05T11:11:09.321763+00:00"}