{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3SW6HUVDQKNRYKII33IRR7WSCL","short_pith_number":"pith:3SW6HUVD","schema_version":"1.0","canonical_sha256":"dcade3d2a3829b1c2908ded118fed212c2677d3bcdcb5a3e49f6eb4e75dae6ee","source":{"kind":"arxiv","id":"2412.13387","version":1},"attestation_state":"computed","paper":{"title":"Deep Speech Synthesis from Multimodal Articulatory Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Aditi S. Krishnapriyan, Alan W Black, Bohan Yu, Gopala K. Anumanchipalli, Irene Y. Chen, Kevin Scheck, Peter Wu, Shinji Watanabe, Tanja Schultz","submitted_at":"2024-12-17T23:55:00Z","abstract_excerpt":"The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a multimodal pre-training framework. On single-speaker speech synthesis tasks from real-time magnetic resonance imaging and surface electromyography inputs, the intelligibility of synthesized outputs improves noticeably. For example, compared to prior work, utilizing our proposed transfer learning methods improves the MRI-to-speech performance by 36% word error rat"},"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":"2412.13387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-17T23:55:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"22d0edb9dab9fb68e688d4cd0aa62b7b43aa7093e03f0d9dd814ed15d4641519","abstract_canon_sha256":"093886351da074ec1de9067d06a5670fe679c9e579ceb8825f7d051147366917"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:00.840354Z","signature_b64":"Nffhmhfx02yVmhOo9p1ry/0+pYNod6pCW4gKMJbHEH0tDLuF9OMfUFeL3eh1Q3mepOOHp8caK0ljJKO2xewmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcade3d2a3829b1c2908ded118fed212c2677d3bcdcb5a3e49f6eb4e75dae6ee","last_reissued_at":"2026-07-05T09:51:00.839845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:00.839845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Speech Synthesis from Multimodal Articulatory Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Aditi S. Krishnapriyan, Alan W Black, Bohan Yu, Gopala K. Anumanchipalli, Irene Y. Chen, Kevin Scheck, Peter Wu, Shinji Watanabe, Tanja Schultz","submitted_at":"2024-12-17T23:55:00Z","abstract_excerpt":"The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a multimodal pre-training framework. On single-speaker speech synthesis tasks from real-time magnetic resonance imaging and surface electromyography inputs, the intelligibility of synthesized outputs improves noticeably. For example, compared to prior work, utilizing our proposed transfer learning methods improves the MRI-to-speech performance by 36% word error rat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13387","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/2412.13387/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":"2412.13387","created_at":"2026-07-05T09:51:00.839903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13387v1","created_at":"2026-07-05T09:51:00.839903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13387","created_at":"2026-07-05T09:51:00.839903+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SW6HUVDQKNR","created_at":"2026-07-05T09:51:00.839903+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SW6HUVDQKNRYKII","created_at":"2026-07-05T09:51:00.839903+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SW6HUVD","created_at":"2026-07-05T09:51:00.839903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL","json":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL.json","graph_json":"https://pith.science/api/pith-number/3SW6HUVDQKNRYKII33IRR7WSCL/graph.json","events_json":"https://pith.science/api/pith-number/3SW6HUVDQKNRYKII33IRR7WSCL/events.json","paper":"https://pith.science/paper/3SW6HUVD"},"agent_actions":{"view_html":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL","download_json":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL.json","view_paper":"https://pith.science/paper/3SW6HUVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13387&json=true","fetch_graph":"https://pith.science/api/pith-number/3SW6HUVDQKNRYKII33IRR7WSCL/graph.json","fetch_events":"https://pith.science/api/pith-number/3SW6HUVDQKNRYKII33IRR7WSCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL/action/storage_attestation","attest_author":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL/action/author_attestation","sign_citation":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL/action/citation_signature","submit_replication":"https://pith.science/pith/3SW6HUVDQKNRYKII33IRR7WSCL/action/replication_record"}},"created_at":"2026-07-05T09:51:00.839903+00:00","updated_at":"2026-07-05T09:51:00.839903+00:00"}