{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XQXJJJR4IPIASYMS5I4IG2C6MR","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":"4921062514adfb33cb5e52a632be2dd1a860599b358dec466069d96b83705489","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-30T18:30:20Z","title_canon_sha256":"dd8ef9cb46127f20822bbd416d63ad4c47d4e8c2c2d7017d4b94b905227b600d"},"schema_version":"1.0","source":{"id":"2205.15370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15370","created_at":"2026-07-05T04:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15370v1","created_at":"2026-07-05T04:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15370","created_at":"2026-07-05T04:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"XQXJJJR4IPIA","created_at":"2026-07-05T04:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"XQXJJJR4IPIASYMS","created_at":"2026-07-05T04:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"XQXJJJR4","created_at":"2026-07-05T04:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:d0eef26f92c45ee3285c915b9d7de60832af519f05902c85c5cb05c9205da52b","target":"graph","created_at":"2026-07-05T04:27:32Z","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/2205.15370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier for adaptive text-to-speech. We train the speaker-conditional diffusion model on large-scale untranscribed datasets for a classifier-free guidance method and further fine-tune the diffusion model on the reference speech of the target speaker for adaptation, which only takes 40 seconds. We demonstrate that Guided-TTS 2 shows comparable performance to high-quality single-speaker ","authors_text":"Heeseung Kim, Sungroh Yoon, Sungwon Kim","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-30T18:30:20Z","title":"Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15370","kind":"arxiv","version":1},"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":"sha256:5efd6c6ac13ebe1f94b247c598d15a64be7f6e6a4159fd14ec8f2ecb8bc53a0c","target":"record","created_at":"2026-07-05T04:27:32Z","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":"4921062514adfb33cb5e52a632be2dd1a860599b358dec466069d96b83705489","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-30T18:30:20Z","title_canon_sha256":"dd8ef9cb46127f20822bbd416d63ad4c47d4e8c2c2d7017d4b94b905227b600d"},"schema_version":"1.0","source":{"id":"2205.15370","kind":"arxiv","version":1}},"canonical_sha256":"bc2e94a63c43d0096192ea3883685e6477d14b8e243d89a7b8883080e03d6c46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc2e94a63c43d0096192ea3883685e6477d14b8e243d89a7b8883080e03d6c46","first_computed_at":"2026-07-05T04:27:32.319264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:32.319264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jqb1rj2iYOcv+LXeI+fGP/AMyDwAppZ87z8CF+MzddWcKcOJs1BhM7VP+wEFVAIvJuOyLPJiREgHTJRq2/3JCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:32.319669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5efd6c6ac13ebe1f94b247c598d15a64be7f6e6a4159fd14ec8f2ecb8bc53a0c","sha256:d0eef26f92c45ee3285c915b9d7de60832af519f05902c85c5cb05c9205da52b"],"state_sha256":"b7b1d5e0e932423e2daea35677b54a049f2a322154b596d46d2756640f5ee45d"}