{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H2ECDZMDXPH3C4UFPAFXVLTPZV","short_pith_number":"pith:H2ECDZMD","schema_version":"1.0","canonical_sha256":"3e8821e583bbcfb17285780b7aae6fcd5f8f212b03d2013e8c164685d16180d9","source":{"kind":"arxiv","id":"2501.04379","version":1},"attestation_state":"computed","paper":{"title":"Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoning Xu, Huimeng Wang, Jiajun Deng, Mengzhe Geng, Shujie Hu, Xunying Liu, Xurong Xie, Youjun Chen, Zhaoqing Li","submitted_at":"2025-01-08T09:45:14Z","abstract_excerpt":"Discrete tokens extracted provide efficient and domain adaptable speech features. Their application to disordered speech that exhibits articulation imprecision and large mismatch against normal voice remains unexplored. To improve their phonetic discrimination that is weakened during unsupervised K-means or vector quantization of continuous features, this paper proposes novel phone-purity guided (PPG) discrete tokens for dysarthric speech recognition. Phonetic label supervision is used to regularize maximum likelihood and reconstruction error costs used in standard K-means and VAE-VQ based dis"},"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":"2501.04379","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-08T09:45:14Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"de91f2631d4c12e6e770817fa984af65a8b723e21df924eb7764cb81c18b7d8b","abstract_canon_sha256":"f574042feb706d135fe1d7cbe675dd71027ec2e42b315413ea8f0124dd1043c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:34.070901Z","signature_b64":"kn8kuiJK0w2d6EPutImUmVIllcCqGqnvdehZqTjPCSCF8OlemYKW7gSpyUftNcgfpLa4a4n7axq0+zBvnYwBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8821e583bbcfb17285780b7aae6fcd5f8f212b03d2013e8c164685d16180d9","last_reissued_at":"2026-07-05T09:58:34.070434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:34.070434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoning Xu, Huimeng Wang, Jiajun Deng, Mengzhe Geng, Shujie Hu, Xunying Liu, Xurong Xie, Youjun Chen, Zhaoqing Li","submitted_at":"2025-01-08T09:45:14Z","abstract_excerpt":"Discrete tokens extracted provide efficient and domain adaptable speech features. Their application to disordered speech that exhibits articulation imprecision and large mismatch against normal voice remains unexplored. To improve their phonetic discrimination that is weakened during unsupervised K-means or vector quantization of continuous features, this paper proposes novel phone-purity guided (PPG) discrete tokens for dysarthric speech recognition. Phonetic label supervision is used to regularize maximum likelihood and reconstruction error costs used in standard K-means and VAE-VQ based dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04379","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/2501.04379/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":"2501.04379","created_at":"2026-07-05T09:58:34.070489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04379v1","created_at":"2026-07-05T09:58:34.070489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04379","created_at":"2026-07-05T09:58:34.070489+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2ECDZMDXPH3","created_at":"2026-07-05T09:58:34.070489+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2ECDZMDXPH3C4UF","created_at":"2026-07-05T09:58:34.070489+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2ECDZMD","created_at":"2026-07-05T09:58:34.070489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13253","citing_title":"Towards Personalized Federated Learning for Dysarthric Speech Recognition","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV","json":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV.json","graph_json":"https://pith.science/api/pith-number/H2ECDZMDXPH3C4UFPAFXVLTPZV/graph.json","events_json":"https://pith.science/api/pith-number/H2ECDZMDXPH3C4UFPAFXVLTPZV/events.json","paper":"https://pith.science/paper/H2ECDZMD"},"agent_actions":{"view_html":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV","download_json":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV.json","view_paper":"https://pith.science/paper/H2ECDZMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04379&json=true","fetch_graph":"https://pith.science/api/pith-number/H2ECDZMDXPH3C4UFPAFXVLTPZV/graph.json","fetch_events":"https://pith.science/api/pith-number/H2ECDZMDXPH3C4UFPAFXVLTPZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV/action/storage_attestation","attest_author":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV/action/author_attestation","sign_citation":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV/action/citation_signature","submit_replication":"https://pith.science/pith/H2ECDZMDXPH3C4UFPAFXVLTPZV/action/replication_record"}},"created_at":"2026-07-05T09:58:34.070489+00:00","updated_at":"2026-07-05T09:58:34.070489+00:00"}