{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZZCEQ3FP4FZIYIL7W2U5WUQQYF","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":"c092b43e417814144fdafafe2ba7de38e7d5df304b53f6edbab1cbac1b6fe2cf","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-31T12:45:43Z","title_canon_sha256":"192b178edc0318ec37a20ea95adb543ecd619638a517311b56c406998ab844cb"},"schema_version":"1.0","source":{"id":"2401.17796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17796","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17796v1","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17796","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZZCEQ3FP4FZI","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZZCEQ3FP4FZIYIL7","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZZCEQ3FP","created_at":"2026-07-05T07:39:42Z"}],"graph_snapshots":[{"event_id":"sha256:04e089ea10efaee525bbf1a3a182a3360899bd75f4a314da526351529a96dec6","target":"graph","created_at":"2026-07-05T07:39:42Z","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/2401.17796/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 by improving the intelligibility and naturalness. This is a challenging task especially for patients with severe dysarthria and speaking in complex, noisy acoustic environments. To address these challenges, we propose a novel multi-modal framework to utilize visual information, e.g., lip movements, in DSR as extra clues for reconstructing the highly abnormal pronunciations. The multi-modal framework consists of: (i) a multi-modal encoder to extract robust phoneme embeddings from dysarthric speech with","authors_text":"Disong Wang, Helen Meng, Xixin Wu, Xueyuan Chen, Xunying Liu, Yuejiao Wang, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-31T12:45:43Z","title":"Exploiting Audio-Visual Features with Pretrained AV-HuBERT for Multi-Modal Dysarthric Speech Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17796","kind":"arxiv","version":1},"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:ed019af9d17961730f2346ef4fec327a3bc1542d4acb1489cdb408f14cdf9362","target":"record","created_at":"2026-07-05T07:39:42Z","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":"c092b43e417814144fdafafe2ba7de38e7d5df304b53f6edbab1cbac1b6fe2cf","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-31T12:45:43Z","title_canon_sha256":"192b178edc0318ec37a20ea95adb543ecd619638a517311b56c406998ab844cb"},"schema_version":"1.0","source":{"id":"2401.17796","kind":"arxiv","version":1}},"canonical_sha256":"ce44486cafe1728c217fb6a9db5210c16bd4b687a71a5e33c130e13cf49cd3c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce44486cafe1728c217fb6a9db5210c16bd4b687a71a5e33c130e13cf49cd3c1","first_computed_at":"2026-07-05T07:39:42.562863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:42.562863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cHPGP1QdZbQYi4HkIwSWKyy4fzrEEQIhA3M+glw5R+T1XQHao2K48Kv/vjC8SSldQxvoKScK//pYowGkX1+QDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:42.563211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed019af9d17961730f2346ef4fec327a3bc1542d4acb1489cdb408f14cdf9362","sha256:04e089ea10efaee525bbf1a3a182a3360899bd75f4a314da526351529a96dec6"],"state_sha256":"8ce633529798f1223eb68c8cdf2ec442bc002350e43171957e9e72188690e1df"}