{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7GZVESTQDD7DF465P2KE5PZDI","short_pith_number":"pith:Y7GZVEST","schema_version":"1.0","canonical_sha256":"c7cd9a925380c7f1979eebf4a275f91a17f165c550e2c8019d25262d6bcac36d","source":{"kind":"arxiv","id":"2608.00803","version":1},"attestation_state":"computed","paper":{"title":"SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.SD","authors_text":"Cheng Zhang, Fran\\c{c}ois Guimbreti\\`ere, Jiacheng Liu, Ruidong Zhang","submitted_at":"2026-08-01T18:03:37Z","abstract_excerpt":"Wearable silent speech interfaces (SSIs) are limited to small, closed vocabularies. Approaches achieving larger vocabularies require obtrusive hardware such as facial electrodes. We present SoniSpeech, the first large-scale, open-vocabulary, trimodal dataset for wearable SSI using acoustic-sensing eyewear. It contains 34 hours across 18,000 utterances with three synchronized modalities: ultrasound echo profiles, voiced audio, and frontal video, in both voiced and silent modes. The corpus draws from the SODA dialogue dataset, providing contemporary conversational English with 5,356 unique words"},"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":"2608.00803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-01T18:03:37Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"b47d298543fc3c2ce71a18093e765d5ea303b245c39d632f53c0058245361109","abstract_canon_sha256":"168e0215639ccff76dc41c12fe04b5eb43a31881ba1dd2bad789f9393ea8d685"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:55:10.665266Z","signature_b64":"JNQ/vUZ1om8rUGS+JUJufHmTs0DYNQn5RLw0LUoeWQ8NyIxkesNtHjCZ31PMXSM5o/oLanHQD5laKwHKWhzuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7cd9a925380c7f1979eebf4a275f91a17f165c550e2c8019d25262d6bcac36d","last_reissued_at":"2026-08-04T01:55:10.663781Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:55:10.663781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.SD","authors_text":"Cheng Zhang, Fran\\c{c}ois Guimbreti\\`ere, Jiacheng Liu, Ruidong Zhang","submitted_at":"2026-08-01T18:03:37Z","abstract_excerpt":"Wearable silent speech interfaces (SSIs) are limited to small, closed vocabularies. Approaches achieving larger vocabularies require obtrusive hardware such as facial electrodes. We present SoniSpeech, the first large-scale, open-vocabulary, trimodal dataset for wearable SSI using acoustic-sensing eyewear. It contains 34 hours across 18,000 utterances with three synchronized modalities: ultrasound echo profiles, voiced audio, and frontal video, in both voiced and silent modes. The corpus draws from the SODA dialogue dataset, providing contemporary conversational English with 5,356 unique words"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00803","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/2608.00803/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":"2608.00803","created_at":"2026-08-04T01:55:10.665078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00803v1","created_at":"2026-08-04T01:55:10.665078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00803","created_at":"2026-08-04T01:55:10.665078+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7GZVESTQDD7","created_at":"2026-08-04T01:55:10.665078+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7GZVESTQDD7DF46","created_at":"2026-08-04T01:55:10.665078+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7GZVEST","created_at":"2026-08-04T01:55:10.665078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00803","citing_title":"SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI","json":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI.json","graph_json":"https://pith.science/api/pith-number/Y7GZVESTQDD7DF465P2KE5PZDI/graph.json","events_json":"https://pith.science/api/pith-number/Y7GZVESTQDD7DF465P2KE5PZDI/events.json","paper":"https://pith.science/paper/Y7GZVEST"},"agent_actions":{"view_html":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI","download_json":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI.json","view_paper":"https://pith.science/paper/Y7GZVEST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00803&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7GZVESTQDD7DF465P2KE5PZDI/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7GZVESTQDD7DF465P2KE5PZDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI/action/storage_attestation","attest_author":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI/action/author_attestation","sign_citation":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI/action/citation_signature","submit_replication":"https://pith.science/pith/Y7GZVESTQDD7DF465P2KE5PZDI/action/replication_record"}},"created_at":"2026-08-04T01:55:10.665078+00:00","updated_at":"2026-08-04T01:55:10.665078+00:00"}