{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F54UMVHVSZYBHWQXLL27V5LTUR","short_pith_number":"pith:F54UMVHV","canonical_record":{"source":{"id":"2406.08336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T15:42:21Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"a22ebfa16bc0f0aeaaecafe21efea0a46505e1bf07d697014c9038903a9f0b5c","abstract_canon_sha256":"c164add008047241bb989aff9d926ffd4e3bb0c87688273cd5726e81b8d1929a"},"schema_version":"1.0"},"canonical_sha256":"2f794654f5967013da175af5faf573a473bb879934be57fce11c4aad26f9a43f","source":{"kind":"arxiv","id":"2406.08336","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F54UMVHVSZYBHWQXLL27V5LTUR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T15:42:21Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"a22ebfa16bc0f0aeaaecafe21efea0a46505e1bf07d697014c9038903a9f0b5c","abstract_canon_sha256":"c164add008047241bb989aff9d926ffd4e3bb0c87688273cd5726e81b8d1929a"},"schema_version":"1.0"},"canonical_sha256":"2f794654f5967013da175af5faf573a473bb879934be57fce11c4aad26f9a43f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:47.281445Z","signature_b64":"Uf5NNASStvMLAa7+YmJl2xZUYTFDGsGjA5jMlU1clcJKhK8gVzM2EqmLu0ikPvWi9POTv0T94I4G0zEowPKrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f794654f5967013da175af5faf573a473bb879934be57fce11c4aad26f9a43f","last_reissued_at":"2026-07-05T08:35:47.280967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:47.280967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08336","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GLvOz6MSKJ7HcyKYwAsPgDVaumPY30yS7pbNbrPcQB6io/pHiW/yUEjH76a2jQxzILnt3d9Sy6XNjxO1Nd7WDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:43:09.443356Z"},"content_sha256":"703e82989ddf17446cad31e15e296377cca7b52737887c07861d5754995f8f38","schema_version":"1.0","event_id":"sha256:703e82989ddf17446cad31e15e296377cca7b52737887c07861d5754995f8f38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F54UMVHVSZYBHWQXLL27V5LTUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dingdong Wang, Dongchao Yang, Helen Meng, Xixin Wu, Xueyuan Chen, Zhiyong Wu","submitted_at":"2024-06-12T15:42:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08336","kind":"arxiv","version":2},"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/2406.08336/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4q/5qRo5zSrzgS6pxuv/+FgerIsHr7EKM3r8tbqhWCZvBwnP9eQJpgvXti9JSsBh3Cw3MN5NzxUM3XxgAFoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:43:09.443878Z"},"content_sha256":"bb21146c1e64ca3d713ec4a23a7849a028e8fb802348911780de7a9bae0edd20","schema_version":"1.0","event_id":"sha256:bb21146c1e64ca3d713ec4a23a7849a028e8fb802348911780de7a9bae0edd20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F54UMVHVSZYBHWQXLL27V5LTUR/bundle.json","state_url":"https://pith.science/pith/F54UMVHVSZYBHWQXLL27V5LTUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F54UMVHVSZYBHWQXLL27V5LTUR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T02:43:09Z","links":{"resolver":"https://pith.science/pith/F54UMVHVSZYBHWQXLL27V5LTUR","bundle":"https://pith.science/pith/F54UMVHVSZYBHWQXLL27V5LTUR/bundle.json","state":"https://pith.science/pith/F54UMVHVSZYBHWQXLL27V5LTUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F54UMVHVSZYBHWQXLL27V5LTUR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dw2HRDUcgcepymZzuM8YlzRRgFU8QCnRMT7zq1CPuB+1TDgOtjQ8VPrzTawfNZQFmmPwAlaT1TjR7P818LZYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:43:09.448684Z","bundle_sha256":"fec87c9b3c0727887f133d913a47e861715a47e5f27233e580af792b758a2575"}}