{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C5B23VBGNZZUX7LPPRMMXP5RSD","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":"4053ad912c12c15fc282af69565cf080493ce7e285f346d6ca738739e3e7f9dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-23T15:01:28Z","title_canon_sha256":"2971470f2ed35273a774c915d5f264fba2187683cd50f05d65c73dd2bcb0aa37"},"schema_version":"1.0","source":{"id":"2605.24618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24618","created_at":"2026-05-26T01:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24618v1","created_at":"2026-05-26T01:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24618","created_at":"2026-05-26T01:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"C5B23VBGNZZU","created_at":"2026-05-26T01:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"C5B23VBGNZZUX7LP","created_at":"2026-05-26T01:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"C5B23VBG","created_at":"2026-05-26T01:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:a3fceb0fc0cb3b34756060156c7b5a2eec935be763e96d29ae4ecf54771f6937","target":"graph","created_at":"2026-05-26T01:03:49Z","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/2605.24618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in zero-shot text-to-speech (TTS) have enabled accurate imitation of reference speech in terms of both speaking style and speaker timbre. However, achieving disentangled control over these aspects from separate references remains a challenging task. Several studies have proposed disentangled speech representations that decompose speech into interpretable attributes (e.g., timbre, prosody, and content), providing a promising foundation for TTS with attribute control from separate references. Yet, how to effectively integrate such representations into TTS systems to achieve indep","authors_text":"Hyunsin Park, Jinhwan Park, Jinkyu Lee, Yoonhyung Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-23T15:01:28Z","title":"FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24618","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:d60ebbb1ef7d042fdabb9c1a95e8c3325957d6a203e2c6662c1eedd170675584","target":"record","created_at":"2026-05-26T01:03:49Z","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":"4053ad912c12c15fc282af69565cf080493ce7e285f346d6ca738739e3e7f9dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-23T15:01:28Z","title_canon_sha256":"2971470f2ed35273a774c915d5f264fba2187683cd50f05d65c73dd2bcb0aa37"},"schema_version":"1.0","source":{"id":"2605.24618","kind":"arxiv","version":1}},"canonical_sha256":"1743add4266e734bfd6f7c58cbbfb190c28cbb13d812a3078c3b41b848a91e9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1743add4266e734bfd6f7c58cbbfb190c28cbb13d812a3078c3b41b848a91e9f","first_computed_at":"2026-05-26T01:03:49.272500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:49.272500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J1Nz1WzBKd7oYtfKTNS6d6L4Aemr081Bd7+P5/C2NDhIOvQ9G7UX82nh2Jj5+nTg1MWCGXH+AP3/hWEsP4x9AQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:49.273254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d60ebbb1ef7d042fdabb9c1a95e8c3325957d6a203e2c6662c1eedd170675584","sha256:a3fceb0fc0cb3b34756060156c7b5a2eec935be763e96d29ae4ecf54771f6937"],"state_sha256":"fc69c67098805ef4e71f19e16b7bbfce7d89399a68f516a42486fed12f8c6921"}