{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:45B6WQFFDQQXQB6YZLEEPW2BYR","short_pith_number":"pith:45B6WQFF","schema_version":"1.0","canonical_sha256":"e743eb40a51c217807d8cac847db41c453fc7efa0e656612cd7ad8ec23586e5e","source":{"kind":"arxiv","id":"2403.05583","version":1},"attestation_state":"computed","paper":{"title":"A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Francis R Willett, Guy Wilson, Reshef Elisha, Shaul Druckmann, Tyler Benster","submitted_at":"2024-03-02T21:15:24Z","abstract_excerpt":"Silent Speech Interfaces (SSIs) offer a noninvasive alternative to brain-computer interfaces for soundless verbal communication. We introduce Multimodal Orofacial Neural Audio (MONA), a system that leverages cross-modal alignment through novel loss functions--cross-contrast (crossCon) and supervised temporal contrast (supTcon)--to train a multimodal model with a shared latent representation. This architecture enables the use of audio-only datasets like LibriSpeech to improve silent speech recognition. Additionally, our introduction of Large Language Model (LLM) Integrated Scoring Adjustment (L"},"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":"2403.05583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-03-02T21:15:24Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"aef635895f647e11fa65d75f64b15081c7e761ed57e968572a6a9d06ecaeddb8","abstract_canon_sha256":"413d403f63fdf90f33b12a0f18fde2d32a0ebe413b1bf33f1dbdabb435855a0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:10.413591Z","signature_b64":"UxQAy9sPEU24L53CWXS3dqSQvRne7pLh8wSqkurXN6wihsltY2HVdMahxvZcefTmM7+4jS0dCMskrKVhfy0zBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e743eb40a51c217807d8cac847db41c453fc7efa0e656612cd7ad8ec23586e5e","last_reissued_at":"2026-07-05T07:54:10.413145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:10.413145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Francis R Willett, Guy Wilson, Reshef Elisha, Shaul Druckmann, Tyler Benster","submitted_at":"2024-03-02T21:15:24Z","abstract_excerpt":"Silent Speech Interfaces (SSIs) offer a noninvasive alternative to brain-computer interfaces for soundless verbal communication. We introduce Multimodal Orofacial Neural Audio (MONA), a system that leverages cross-modal alignment through novel loss functions--cross-contrast (crossCon) and supervised temporal contrast (supTcon)--to train a multimodal model with a shared latent representation. This architecture enables the use of audio-only datasets like LibriSpeech to improve silent speech recognition. Additionally, our introduction of Large Language Model (LLM) Integrated Scoring Adjustment (L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05583","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/2403.05583/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":"2403.05583","created_at":"2026-07-05T07:54:10.413203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05583v1","created_at":"2026-07-05T07:54:10.413203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05583","created_at":"2026-07-05T07:54:10.413203+00:00"},{"alias_kind":"pith_short_12","alias_value":"45B6WQFFDQQX","created_at":"2026-07-05T07:54:10.413203+00:00"},{"alias_kind":"pith_short_16","alias_value":"45B6WQFFDQQXQB6Y","created_at":"2026-07-05T07:54:10.413203+00:00"},{"alias_kind":"pith_short_8","alias_value":"45B6WQFF","created_at":"2026-07-05T07:54:10.413203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.10287","citing_title":"OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR","json":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR.json","graph_json":"https://pith.science/api/pith-number/45B6WQFFDQQXQB6YZLEEPW2BYR/graph.json","events_json":"https://pith.science/api/pith-number/45B6WQFFDQQXQB6YZLEEPW2BYR/events.json","paper":"https://pith.science/paper/45B6WQFF"},"agent_actions":{"view_html":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR","download_json":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR.json","view_paper":"https://pith.science/paper/45B6WQFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05583&json=true","fetch_graph":"https://pith.science/api/pith-number/45B6WQFFDQQXQB6YZLEEPW2BYR/graph.json","fetch_events":"https://pith.science/api/pith-number/45B6WQFFDQQXQB6YZLEEPW2BYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR/action/storage_attestation","attest_author":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR/action/author_attestation","sign_citation":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR/action/citation_signature","submit_replication":"https://pith.science/pith/45B6WQFFDQQXQB6YZLEEPW2BYR/action/replication_record"}},"created_at":"2026-07-05T07:54:10.413203+00:00","updated_at":"2026-07-05T07:54:10.413203+00:00"}