{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KXKXDQSLVQ5ODLZVZGYAXHTAV2","short_pith_number":"pith:KXKXDQSL","schema_version":"1.0","canonical_sha256":"55d571c24bac3ae1af35c9b00b9e60aea6eb7438d486871add9c9df75acaa15a","source":{"kind":"arxiv","id":"2506.03831","version":1},"attestation_state":"computed","paper":{"title":"Conformer-based Ultrasound-to-Speech Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"G\\'abor Gosztolya, Ibrahim Ibrahimov, Zaink\\'o Csaba","submitted_at":"2025-06-04T10:58:39Z","abstract_excerpt":"Deep neural networks have shown promising potential for ultrasound-to-speech conversion task towards Silent Speech Interfaces. In this work, we applied two Conformer-based DNN architectures (Base and one with bi-LSTM) for this task. Speaker-specific models were trained on the data of four speakers from the Ultrasuite-Tal80 dataset, while the generated mel spectrograms were synthesized to audio waveform using a HiFi-GAN vocoder. Compared to a standard 2D-CNN baseline, objective measurements (MSE and mel cepstral distortion) showed no statistically significant improvement for either model. Howev"},"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":"2506.03831","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-04T10:58:39Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"0d0f497aaf110e1f3da8fb3066fe71e6267fde05489361e4246ac6ab31e729ee","abstract_canon_sha256":"a5af45894222d5976495ec7b6d53862725c2319634b14b558386aed4fb47388d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:52.516310Z","signature_b64":"Mfbm+jz/AUx+aTKTXFtk+bT7/Y/ajSgvAPNVg2PvzRma8XFmavkHUdtC212Ef25eQcvt7plT97/geHRyHgz/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d571c24bac3ae1af35c9b00b9e60aea6eb7438d486871add9c9df75acaa15a","last_reissued_at":"2026-07-05T11:15:52.515897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:52.515897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conformer-based Ultrasound-to-Speech Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"G\\'abor Gosztolya, Ibrahim Ibrahimov, Zaink\\'o Csaba","submitted_at":"2025-06-04T10:58:39Z","abstract_excerpt":"Deep neural networks have shown promising potential for ultrasound-to-speech conversion task towards Silent Speech Interfaces. In this work, we applied two Conformer-based DNN architectures (Base and one with bi-LSTM) for this task. Speaker-specific models were trained on the data of four speakers from the Ultrasuite-Tal80 dataset, while the generated mel spectrograms were synthesized to audio waveform using a HiFi-GAN vocoder. Compared to a standard 2D-CNN baseline, objective measurements (MSE and mel cepstral distortion) showed no statistically significant improvement for either model. Howev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03831","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/2506.03831/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":"2506.03831","created_at":"2026-07-05T11:15:52.515963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03831v1","created_at":"2026-07-05T11:15:52.515963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03831","created_at":"2026-07-05T11:15:52.515963+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXKXDQSLVQ5O","created_at":"2026-07-05T11:15:52.515963+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXKXDQSLVQ5ODLZV","created_at":"2026-07-05T11:15:52.515963+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXKXDQSL","created_at":"2026-07-05T11:15:52.515963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03831","citing_title":"Conformer-based Ultrasound-to-Speech Conversion","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2","json":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2.json","graph_json":"https://pith.science/api/pith-number/KXKXDQSLVQ5ODLZVZGYAXHTAV2/graph.json","events_json":"https://pith.science/api/pith-number/KXKXDQSLVQ5ODLZVZGYAXHTAV2/events.json","paper":"https://pith.science/paper/KXKXDQSL"},"agent_actions":{"view_html":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2","download_json":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2.json","view_paper":"https://pith.science/paper/KXKXDQSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03831&json=true","fetch_graph":"https://pith.science/api/pith-number/KXKXDQSLVQ5ODLZVZGYAXHTAV2/graph.json","fetch_events":"https://pith.science/api/pith-number/KXKXDQSLVQ5ODLZVZGYAXHTAV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2/action/storage_attestation","attest_author":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2/action/author_attestation","sign_citation":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2/action/citation_signature","submit_replication":"https://pith.science/pith/KXKXDQSLVQ5ODLZVZGYAXHTAV2/action/replication_record"}},"created_at":"2026-07-05T11:15:52.515963+00:00","updated_at":"2026-07-05T11:15:52.515963+00:00"}