{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F54UMVHVSZYBHWQXLL27V5LTUR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c164add008047241bb989aff9d926ffd4e3bb0c87688273cd5726e81b8d1929a","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T15:42:21Z","title_canon_sha256":"a22ebfa16bc0f0aeaaecafe21efea0a46505e1bf07d697014c9038903a9f0b5c"},"schema_version":"1.0","source":{"id":"2406.08336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08336","created_at":"2026-07-05T08:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08336v2","created_at":"2026-07-05T08:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08336","created_at":"2026-07-05T08:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"F54UMVHVSZYB","created_at":"2026-07-05T08:35:47Z"},{"alias_kind":"pith_short_16","alias_value":"F54UMVHVSZYBHWQX","created_at":"2026-07-05T08:35:47Z"},{"alias_kind":"pith_short_8","alias_value":"F54UMVHV","created_at":"2026-07-05T08:35:47Z"}],"graph_snapshots":[{"event_id":"sha256:bb21146c1e64ca3d713ec4a23a7849a028e8fb802348911780de7a9bae0edd20","target":"graph","created_at":"2026-07-05T08:35:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.08336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural codec language modeling to improve the reconstruction results, especially for the speaker similarity and prosody naturalness. Our proposed model consists of: (i) a multi-modal content encoder to extract robust phoneme embeddings from dysarthric speech with auxiliary visual inputs; (ii) a speaker codec encoder to extract and normalize the speaker-aware codec","authors_text":"Dingdong Wang, Dongchao Yang, Helen Meng, Xixin Wu, Xueyuan Chen, Zhiyong Wu","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T15:42:21Z","title":"CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08336","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:703e82989ddf17446cad31e15e296377cca7b52737887c07861d5754995f8f38","target":"record","created_at":"2026-07-05T08:35:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c164add008047241bb989aff9d926ffd4e3bb0c87688273cd5726e81b8d1929a","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T15:42:21Z","title_canon_sha256":"a22ebfa16bc0f0aeaaecafe21efea0a46505e1bf07d697014c9038903a9f0b5c"},"schema_version":"1.0","source":{"id":"2406.08336","kind":"arxiv","version":2}},"canonical_sha256":"2f794654f5967013da175af5faf573a473bb879934be57fce11c4aad26f9a43f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f794654f5967013da175af5faf573a473bb879934be57fce11c4aad26f9a43f","first_computed_at":"2026-07-05T08:35:47.280967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:47.280967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uf5NNASStvMLAa7+YmJl2xZUYTFDGsGjA5jMlU1clcJKhK8gVzM2EqmLu0ikPvWi9POTv0T94I4G0zEowPKrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:47.281445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:703e82989ddf17446cad31e15e296377cca7b52737887c07861d5754995f8f38","sha256:bb21146c1e64ca3d713ec4a23a7849a028e8fb802348911780de7a9bae0edd20"],"state_sha256":"bb4ef43ca9d250f84b1637b01aa6f695037d3a0c5db0f08cf1cf5b5e315cec56"}