{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRWCU4HUJDKTQFCSUHWTPRSAIL","short_pith_number":"pith:ZRWCU4HU","schema_version":"1.0","canonical_sha256":"cc6c2a70f448d5381452a1ed37c64042d6fdaf4140295d6fa1dbca5867eaac40","source":{"kind":"arxiv","id":"2506.01618","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Enno Hermann, Karl El Hajal, Mathew Magimai.-Doss, Sevada Hovsepyan","submitted_at":"2025-06-02T12:57:36Z","abstract_excerpt":"Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-healthy speech conversion for improved ASR performance. Our approach extends the Rhythm and Voice (RnV) conversion framework by introducing a syllable-based rhythm modeling method suited for dysarthric speech. We assess its impact on ASR by training LF-MMI models and fine-tuning Whisper on converted speech. Experiments on the Torgo corpus reveal that LF-MMI achieves significant word error rate reductions, especially "},"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":"2506.01618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T12:57:36Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"title_canon_sha256":"3d813aefd48bc33624a6cb47f0ba8527d60e4bd7cd325c702954fb346b95b4e0","abstract_canon_sha256":"9c003aa3282dab7f753dd7b8569eb7ae78be8f95ec49c2cdaf091f47353d95f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:16.933694Z","signature_b64":"8Th4J6MgQ5eYEEKCksKKvx71p4QxIYnNmcZyND728AYZpwRUOlkqI6mOerouVO+Doz9avdHQKLUBAqNQsCZEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc6c2a70f448d5381452a1ed37c64042d6fdaf4140295d6fa1dbca5867eaac40","last_reissued_at":"2026-07-05T11:14:16.933259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:16.933259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Enno Hermann, Karl El Hajal, Mathew Magimai.-Doss, Sevada Hovsepyan","submitted_at":"2025-06-02T12:57:36Z","abstract_excerpt":"Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-healthy speech conversion for improved ASR performance. Our approach extends the Rhythm and Voice (RnV) conversion framework by introducing a syllable-based rhythm modeling method suited for dysarthric speech. We assess its impact on ASR by training LF-MMI models and fine-tuning Whisper on converted speech. Experiments on the Torgo corpus reveal that LF-MMI achieves significant word error rate reductions, especially "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01618","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/2506.01618/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":"2506.01618","created_at":"2026-07-05T11:14:16.933308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01618v1","created_at":"2026-07-05T11:14:16.933308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01618","created_at":"2026-07-05T11:14:16.933308+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRWCU4HUJDKT","created_at":"2026-07-05T11:14:16.933308+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRWCU4HUJDKTQFCS","created_at":"2026-07-05T11:14:16.933308+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRWCU4HU","created_at":"2026-07-05T11:14:16.933308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01618","citing_title":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL","json":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL.json","graph_json":"https://pith.science/api/pith-number/ZRWCU4HUJDKTQFCSUHWTPRSAIL/graph.json","events_json":"https://pith.science/api/pith-number/ZRWCU4HUJDKTQFCSUHWTPRSAIL/events.json","paper":"https://pith.science/paper/ZRWCU4HU"},"agent_actions":{"view_html":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL","download_json":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL.json","view_paper":"https://pith.science/paper/ZRWCU4HU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01618&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRWCU4HUJDKTQFCSUHWTPRSAIL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRWCU4HUJDKTQFCSUHWTPRSAIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL/action/storage_attestation","attest_author":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL/action/author_attestation","sign_citation":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL/action/citation_signature","submit_replication":"https://pith.science/pith/ZRWCU4HUJDKTQFCSUHWTPRSAIL/action/replication_record"}},"created_at":"2026-07-05T11:14:16.933308+00:00","updated_at":"2026-07-05T11:14:16.933308+00:00"}