{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C5B23VBGNZZUX7LPPRMMXP5RSD","short_pith_number":"pith:C5B23VBG","schema_version":"1.0","canonical_sha256":"1743add4266e734bfd6f7c58cbbfb190c28cbb13d812a3078c3b41b848a91e9f","source":{"kind":"arxiv","id":"2605.24618","version":1},"attestation_state":"computed","paper":{"title":"FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hyunsin Park, Jinhwan Park, Jinkyu Lee, Yoonhyung Lee","submitted_at":"2026-05-23T15:01:28Z","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"},"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":"2605.24618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-23T15:01:28Z","cross_cats_sorted":[],"title_canon_sha256":"2971470f2ed35273a774c915d5f264fba2187683cd50f05d65c73dd2bcb0aa37","abstract_canon_sha256":"4053ad912c12c15fc282af69565cf080493ce7e285f346d6ca738739e3e7f9dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:49.273254Z","signature_b64":"J1Nz1WzBKd7oYtfKTNS6d6L4Aemr081Bd7+P5/C2NDhIOvQ9G7UX82nh2Jj5+nTg1MWCGXH+AP3/hWEsP4x9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1743add4266e734bfd6f7c58cbbfb190c28cbb13d812a3078c3b41b848a91e9f","last_reissued_at":"2026-05-26T01:03:49.272500Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:49.272500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hyunsin Park, Jinhwan Park, Jinkyu Lee, Yoonhyung Lee","submitted_at":"2026-05-23T15:01:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24618","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/2605.24618/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":"2605.24618","created_at":"2026-05-26T01:03:49.272624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24618v1","created_at":"2026-05-26T01:03:49.272624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24618","created_at":"2026-05-26T01:03:49.272624+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5B23VBGNZZU","created_at":"2026-05-26T01:03:49.272624+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5B23VBGNZZUX7LP","created_at":"2026-05-26T01:03:49.272624+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5B23VBG","created_at":"2026-05-26T01:03:49.272624+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/C5B23VBGNZZUX7LPPRMMXP5RSD","json":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD.json","graph_json":"https://pith.science/api/pith-number/C5B23VBGNZZUX7LPPRMMXP5RSD/graph.json","events_json":"https://pith.science/api/pith-number/C5B23VBGNZZUX7LPPRMMXP5RSD/events.json","paper":"https://pith.science/paper/C5B23VBG"},"agent_actions":{"view_html":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD","download_json":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD.json","view_paper":"https://pith.science/paper/C5B23VBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24618&json=true","fetch_graph":"https://pith.science/api/pith-number/C5B23VBGNZZUX7LPPRMMXP5RSD/graph.json","fetch_events":"https://pith.science/api/pith-number/C5B23VBGNZZUX7LPPRMMXP5RSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD/action/storage_attestation","attest_author":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD/action/author_attestation","sign_citation":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD/action/citation_signature","submit_replication":"https://pith.science/pith/C5B23VBGNZZUX7LPPRMMXP5RSD/action/replication_record"}},"created_at":"2026-05-26T01:03:49.272624+00:00","updated_at":"2026-05-26T01:03:49.272624+00:00"}