{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MRTX5GVLDSI4P2V5ISH2CMB4VC","short_pith_number":"pith:MRTX5GVL","schema_version":"1.0","canonical_sha256":"64677e9aab1c91c7eabd448fa1303ca8926c64a085d9301753791bea613ceecb","source":{"kind":"arxiv","id":"2107.12051","version":1},"attestation_state":"computed","paper":{"title":"Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexandra Mark\\'o, Amin Honarmandi Shandiz, Csaba Zaink\\'o, G\\'abor Gosztolya, G\\'eza N\\'emeth, L\\'aszl\\'o T\\'oth, Tam\\'as G\\'abor Csap\\'o","submitted_at":"2021-07-26T09:19:20Z","abstract_excerpt":"For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation of a Tacotron2 text-to-speech model to improve the final synthesis quality of ultrasound-based articulatory-to-acoustic mapping with a limited database. We use a multi-speaker pre-trained Tacotron2 TTS model and a pre-trained WaveGlow neural vocoder. The articulatory-to-acoustic conversion contains three steps: 1) from a sequence of ultrasound tongue image r"},"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":"2107.12051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-07-26T09:19:20Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"9771aab996f45dd4f3702eed6c49d1e3152d91dbda9187b5d16691d7e2ed82a0","abstract_canon_sha256":"c33c6b80989088bd14413b36ff15c930b209d9d975207d4fbbb1eb15a6da3c66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:39.684795Z","signature_b64":"DcRLMgESO8rBk4bwQlJ5amOkGj1BRfnDuXoqB1ykD+ewiRp7epeuN7Q79c4CYNUD46kT0Gfm0E/p1/ObqyzmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64677e9aab1c91c7eabd448fa1303ca8926c64a085d9301753791bea613ceecb","last_reissued_at":"2026-07-05T03:00:39.684402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:39.684402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexandra Mark\\'o, Amin Honarmandi Shandiz, Csaba Zaink\\'o, G\\'abor Gosztolya, G\\'eza N\\'emeth, L\\'aszl\\'o T\\'oth, Tam\\'as G\\'abor Csap\\'o","submitted_at":"2021-07-26T09:19:20Z","abstract_excerpt":"For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation of a Tacotron2 text-to-speech model to improve the final synthesis quality of ultrasound-based articulatory-to-acoustic mapping with a limited database. We use a multi-speaker pre-trained Tacotron2 TTS model and a pre-trained WaveGlow neural vocoder. The articulatory-to-acoustic conversion contains three steps: 1) from a sequence of ultrasound tongue image r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12051","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/2107.12051/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":"2107.12051","created_at":"2026-07-05T03:00:39.684456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12051v1","created_at":"2026-07-05T03:00:39.684456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12051","created_at":"2026-07-05T03:00:39.684456+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRTX5GVLDSI4","created_at":"2026-07-05T03:00:39.684456+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRTX5GVLDSI4P2V5","created_at":"2026-07-05T03:00:39.684456+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRTX5GVL","created_at":"2026-07-05T03:00:39.684456+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/MRTX5GVLDSI4P2V5ISH2CMB4VC","json":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC.json","graph_json":"https://pith.science/api/pith-number/MRTX5GVLDSI4P2V5ISH2CMB4VC/graph.json","events_json":"https://pith.science/api/pith-number/MRTX5GVLDSI4P2V5ISH2CMB4VC/events.json","paper":"https://pith.science/paper/MRTX5GVL"},"agent_actions":{"view_html":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC","download_json":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC.json","view_paper":"https://pith.science/paper/MRTX5GVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12051&json=true","fetch_graph":"https://pith.science/api/pith-number/MRTX5GVLDSI4P2V5ISH2CMB4VC/graph.json","fetch_events":"https://pith.science/api/pith-number/MRTX5GVLDSI4P2V5ISH2CMB4VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC/action/storage_attestation","attest_author":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC/action/author_attestation","sign_citation":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC/action/citation_signature","submit_replication":"https://pith.science/pith/MRTX5GVLDSI4P2V5ISH2CMB4VC/action/replication_record"}},"created_at":"2026-07-05T03:00:39.684456+00:00","updated_at":"2026-07-05T03:00:39.684456+00:00"}