{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5SCMLEPXYZVLRFWKYBFMIVD2C6","short_pith_number":"pith:5SCMLEPX","schema_version":"1.0","canonical_sha256":"ec84c591f7c66ab896cac04ac4547a17a86be510f62bc93c941d4705b191487f","source":{"kind":"arxiv","id":"2506.00350","version":1},"attestation_state":"computed","paper":{"title":"DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dongchao Yang, Helen Meng, Jing Xu, Minglin Wu, Wenxuan Wu, Xixin Wu, Xueyuan Chen, Zhiyong Wu","submitted_at":"2025-05-31T02:23:38Z","abstract_excerpt":"Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility and poor speaker similarity. In this study, we introduce a novel diffusion-based DSR system that leverages a latent diffusion model to enhance the quality of speech reconstruction. Our model comprises: (i) a speech content encoder for phoneme embedding restoration via pre-trained self-supervised learning (SSL) speech foundation models; (ii) a speaker identit"},"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":"2506.00350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-31T02:23:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"bcb3ecd2c9e0e2d5aed5924133441dc27cd13dd5927aa81e14045d2bb9512104","abstract_canon_sha256":"c20c98cf1a96736715a1a48a2051ef81e876c7dd2eb13c48f1d991a0bf082fc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:33.082924Z","signature_b64":"plmFZAvu24a5vuCT5/JGbCmNgVU4hO4/w1kRcah6/GkHRUp/qS+84WdnhVTDfnXPSx8i85BXtuQNe0z1CtB/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec84c591f7c66ab896cac04ac4547a17a86be510f62bc93c941d4705b191487f","last_reissued_at":"2026-07-05T11:13:33.082427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:33.082427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dongchao Yang, Helen Meng, Jing Xu, Minglin Wu, Wenxuan Wu, Xixin Wu, Xueyuan Chen, Zhiyong Wu","submitted_at":"2025-05-31T02:23:38Z","abstract_excerpt":"Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility and poor speaker similarity. In this study, we introduce a novel diffusion-based DSR system that leverages a latent diffusion model to enhance the quality of speech reconstruction. Our model comprises: (i) a speech content encoder for phoneme embedding restoration via pre-trained self-supervised learning (SSL) speech foundation models; (ii) a speaker identit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00350","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/2506.00350/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":"2506.00350","created_at":"2026-07-05T11:13:33.082503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00350v1","created_at":"2026-07-05T11:13:33.082503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00350","created_at":"2026-07-05T11:13:33.082503+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SCMLEPXYZVL","created_at":"2026-07-05T11:13:33.082503+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SCMLEPXYZVLRFWK","created_at":"2026-07-05T11:13:33.082503+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SCMLEPX","created_at":"2026-07-05T11:13:33.082503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6","json":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6.json","graph_json":"https://pith.science/api/pith-number/5SCMLEPXYZVLRFWKYBFMIVD2C6/graph.json","events_json":"https://pith.science/api/pith-number/5SCMLEPXYZVLRFWKYBFMIVD2C6/events.json","paper":"https://pith.science/paper/5SCMLEPX"},"agent_actions":{"view_html":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6","download_json":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6.json","view_paper":"https://pith.science/paper/5SCMLEPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00350&json=true","fetch_graph":"https://pith.science/api/pith-number/5SCMLEPXYZVLRFWKYBFMIVD2C6/graph.json","fetch_events":"https://pith.science/api/pith-number/5SCMLEPXYZVLRFWKYBFMIVD2C6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6/action/storage_attestation","attest_author":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6/action/author_attestation","sign_citation":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6/action/citation_signature","submit_replication":"https://pith.science/pith/5SCMLEPXYZVLRFWKYBFMIVD2C6/action/replication_record"}},"created_at":"2026-07-05T11:13:33.082503+00:00","updated_at":"2026-07-05T11:13:33.082503+00:00"}