{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KDJTNWOWWXPHOSK5UWVZ4FYP6H","short_pith_number":"pith:KDJTNWOW","canonical_record":{"source":{"id":"2211.09383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T07:17:24Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"8f3714c8a258981a0268b8426eaa4fdd6dc49a42fa174fe993ced476f554258a","abstract_canon_sha256":"dde767141ea7cad3bdbd5da8efb61fcc19ac61bd29521cdd01b7bdce4f7340a1"},"schema_version":"1.0"},"canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","source":{"kind":"arxiv","id":"2211.09383","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KDJTNWOWWXPHOSK5UWVZ4FYP6H","target":"record","payload":{"canonical_record":{"source":{"id":"2211.09383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T07:17:24Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"8f3714c8a258981a0268b8426eaa4fdd6dc49a42fa174fe993ced476f554258a","abstract_canon_sha256":"dde767141ea7cad3bdbd5da8efb61fcc19ac61bd29521cdd01b7bdce4f7340a1"},"schema_version":"1.0"},"canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:52.945134Z","signature_b64":"E8vyuSiicEkbjmrBZvyHSDek/fEo9S0rQfkNOoGZVT2viyVhvvFHxd5A6Nv8yR7HpsX1yPXXF2xQHJTZo1ITAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","last_reissued_at":"2026-07-05T05:50:52.944718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:52.944718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.09383","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:50:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFRRirhgDBY9ZrQCjNIkuruaoiK7IsAREExxN1fdfh0MqCXJexjTkRTJyDAtT/xpnYS7Pf+B218bt9fK5jQrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:16:00.968261Z"},"content_sha256":"4c58b2a64619ef7976db17026b8b90cd1de164f4672ca0928477af8e25ef5b17","schema_version":"1.0","event_id":"sha256:4c58b2a64619ef7976db17026b8b90cd1de164f4672ca0928477af8e25ef5b17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KDJTNWOWWXPHOSK5UWVZ4FYP6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongchan Min, Minki Kang, Sung Ju Hwang","submitted_at":"2022-11-17T07:17:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09383","kind":"arxiv","version":2},"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/2211.09383/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:50:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSi91ydRvfEvRcx4Bv3AAPdvtjAh6nKvdkHM1ZhcmMUOf1gOVt4E71i7ZrGQ82rgJ0rkDgoLtVD0px3QjfXpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:16:00.968854Z"},"content_sha256":"f4e8d4a2153c1c05c3b8559e3354164940d66941d57cd9bab5e4338103962e86","schema_version":"1.0","event_id":"sha256:f4e8d4a2153c1c05c3b8559e3354164940d66941d57cd9bab5e4338103962e86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/bundle.json","state_url":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T02:16:00Z","links":{"resolver":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H","bundle":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/bundle.json","state":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMWqSWKVUHBjs8CdT0ljYRsI4BKVIGFB7RXEtCuazzUkcpv7aOOb1VKCBzph/BImfgHEFj4vgUU4lM9zDll7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:16:00.973939Z","bundle_sha256":"cc26dacaeb4d78eab420ac55e025b1b41daec5dc77956f59eaa5dcd97c874703"}}