{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2V2QVJHUQF4XBXGKC43O7YOALM","short_pith_number":"pith:2V2QVJHU","schema_version":"1.0","canonical_sha256":"d5750aa4f4817970dcca1736efe1c05b2618bee49e3235aefd779cc0369410f2","source":{"kind":"arxiv","id":"2107.08795","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning with Dynamic Transformer for Text to Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chendong Zhao, Jianzong Wang, Jie Liu, Jing Xiao, Xiaoyang Qu, Zhenhou Hong","submitted_at":"2021-07-09T03:34:18Z","abstract_excerpt":"Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets. Due to privacy and security issues, the original datasets are usually unavailable directly. Recently, federated learning proposes a popular distributed machine learning paradigm with an enhanced privacy protection mechanism. It offers a practical and secure framework for data owners to collaborate with others, thus obtaining a better global model trained on the larger dataset. However, due to the high complexity of transformer models, the convergence pr"},"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":"2107.08795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T03:34:18Z","cross_cats_sorted":[],"title_canon_sha256":"65b6611b69d00b093af8caef2205e98708b774086986d59f29f03c42a12f3965","abstract_canon_sha256":"d21e2dccb6873d94b64cf49ea2ba019a499dc7171729e4890cb7b0f2f6e74f35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:53.162713Z","signature_b64":"7wZPvvsvKRI0vuTVo7QnEiXVQaVp1EuSMEF8QIIDBpzjBgHtDRTNN5rmsnog51o3tIkKDRN5RusrrzWsu4EbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5750aa4f4817970dcca1736efe1c05b2618bee49e3235aefd779cc0369410f2","last_reissued_at":"2026-07-05T02:58:53.162195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:53.162195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Dynamic Transformer for Text to Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chendong Zhao, Jianzong Wang, Jie Liu, Jing Xiao, Xiaoyang Qu, Zhenhou Hong","submitted_at":"2021-07-09T03:34:18Z","abstract_excerpt":"Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets. Due to privacy and security issues, the original datasets are usually unavailable directly. Recently, federated learning proposes a popular distributed machine learning paradigm with an enhanced privacy protection mechanism. It offers a practical and secure framework for data owners to collaborate with others, thus obtaining a better global model trained on the larger dataset. However, due to the high complexity of transformer models, the convergence pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08795","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/2107.08795/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":"2107.08795","created_at":"2026-07-05T02:58:53.162256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08795v1","created_at":"2026-07-05T02:58:53.162256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08795","created_at":"2026-07-05T02:58:53.162256+00:00"},{"alias_kind":"pith_short_12","alias_value":"2V2QVJHUQF4X","created_at":"2026-07-05T02:58:53.162256+00:00"},{"alias_kind":"pith_short_16","alias_value":"2V2QVJHUQF4XBXGK","created_at":"2026-07-05T02:58:53.162256+00:00"},{"alias_kind":"pith_short_8","alias_value":"2V2QVJHU","created_at":"2026-07-05T02:58:53.162256+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/2V2QVJHUQF4XBXGKC43O7YOALM","json":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM.json","graph_json":"https://pith.science/api/pith-number/2V2QVJHUQF4XBXGKC43O7YOALM/graph.json","events_json":"https://pith.science/api/pith-number/2V2QVJHUQF4XBXGKC43O7YOALM/events.json","paper":"https://pith.science/paper/2V2QVJHU"},"agent_actions":{"view_html":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM","download_json":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM.json","view_paper":"https://pith.science/paper/2V2QVJHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08795&json=true","fetch_graph":"https://pith.science/api/pith-number/2V2QVJHUQF4XBXGKC43O7YOALM/graph.json","fetch_events":"https://pith.science/api/pith-number/2V2QVJHUQF4XBXGKC43O7YOALM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM/action/storage_attestation","attest_author":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM/action/author_attestation","sign_citation":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM/action/citation_signature","submit_replication":"https://pith.science/pith/2V2QVJHUQF4XBXGKC43O7YOALM/action/replication_record"}},"created_at":"2026-07-05T02:58:53.162256+00:00","updated_at":"2026-07-05T02:58:53.162256+00:00"}