{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KDJTNWOWWXPHOSK5UWVZ4FYP6H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dde767141ea7cad3bdbd5da8efb61fcc19ac61bd29521cdd01b7bdce4f7340a1","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T07:17:24Z","title_canon_sha256":"8f3714c8a258981a0268b8426eaa4fdd6dc49a42fa174fe993ced476f554258a"},"schema_version":"1.0","source":{"id":"2211.09383","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09383","created_at":"2026-07-05T05:50:52Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09383v2","created_at":"2026-07-05T05:50:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09383","created_at":"2026-07-05T05:50:52Z"},{"alias_kind":"pith_short_12","alias_value":"KDJTNWOWWXPH","created_at":"2026-07-05T05:50:52Z"},{"alias_kind":"pith_short_16","alias_value":"KDJTNWOWWXPHOSK5","created_at":"2026-07-05T05:50:52Z"},{"alias_kind":"pith_short_8","alias_value":"KDJTNWOW","created_at":"2026-07-05T05:50:52Z"}],"graph_snapshots":[{"event_id":"sha256:f4e8d4a2153c1c05c3b8559e3354164940d66941d57cd9bab5e4338103962e86","target":"graph","created_at":"2026-07-05T05:50:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.09383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory performance, due to their suboptimal accuracy in mimicking the target speakers' styles. In this work, we present Grad-StyleSpeech, which is an any-speaker adaptive TTS framework that is based on a diffusion model that can generate highly natural speech with extremely high similarity to target speakers' voice, given a few seconds of reference speech. Grad-Sty","authors_text":"Dongchan Min, Minki Kang, Sung Ju Hwang","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T07:17:24Z","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09383","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c58b2a64619ef7976db17026b8b90cd1de164f4672ca0928477af8e25ef5b17","target":"record","created_at":"2026-07-05T05:50:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dde767141ea7cad3bdbd5da8efb61fcc19ac61bd29521cdd01b7bdce4f7340a1","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T07:17:24Z","title_canon_sha256":"8f3714c8a258981a0268b8426eaa4fdd6dc49a42fa174fe993ced476f554258a"},"schema_version":"1.0","source":{"id":"2211.09383","kind":"arxiv","version":2}},"canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","first_computed_at":"2026-07-05T05:50:52.944718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:52.944718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E8vyuSiicEkbjmrBZvyHSDek/fEo9S0rQfkNOoGZVT2viyVhvvFHxd5A6Nv8yR7HpsX1yPXXF2xQHJTZo1ITAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:52.945134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09383","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c58b2a64619ef7976db17026b8b90cd1de164f4672ca0928477af8e25ef5b17","sha256:f4e8d4a2153c1c05c3b8559e3354164940d66941d57cd9bab5e4338103962e86"],"state_sha256":"121eefe9fa6b95560dcabba91950617d7b18b44889c9e2b6ece572cc160c4773"}