{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IHCXOTR25MTD4LVECE2J6QB3RH","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":"de870e36cafe2f41c039b765cd48e30f6cde6d5f968467a8f3b64b47c428ff2a","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-01T14:40:51Z","title_canon_sha256":"a22386304372f3d922ef6ae3a49c2fd787f5cbd543a8cf74871304ebced8ee44"},"schema_version":"1.0","source":{"id":"2507.00808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00808","created_at":"2026-07-05T11:30:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00808v2","created_at":"2026-07-05T11:30:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00808","created_at":"2026-07-05T11:30:46Z"},{"alias_kind":"pith_short_12","alias_value":"IHCXOTR25MTD","created_at":"2026-07-05T11:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"IHCXOTR25MTD4LVE","created_at":"2026-07-05T11:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"IHCXOTR2","created_at":"2026-07-05T11:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:76c865f4949bd0592dbeb17ef463251c322348a3b512c5187ae86376f713aa3f","target":"graph","created_at":"2026-07-05T11:30:46Z","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/2507.00808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice directors often iteratively refine voice actors' performances by providing feedback to achieve the desired outcome. While this iterative feedback-based refinement process is important in actual recordings, it has been overlooked in text-to-speech synthesis (TTS). As a result, fine-grained style refinement after the initial synthesis is not possible, even though the synthesized speech often deviates from the user's intended style. To address this issue, we propose a TTS method with multi-step interaction that allows users to intuitively and rapidly refine synthesized speech. Our approach ","authors_text":"Aya Watanabe, Hiroki Kanagawa, Kenichi Fujita, Yusuke Ijima","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-01T14:40:51Z","title":"Multi-interaction TTS toward professional recording reproduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00808","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":"sha256:596cd23ccdc2a652558f9444a10025f0ac19139211d811c749b1327228830862","target":"record","created_at":"2026-07-05T11:30:46Z","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":"de870e36cafe2f41c039b765cd48e30f6cde6d5f968467a8f3b64b47c428ff2a","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-01T14:40:51Z","title_canon_sha256":"a22386304372f3d922ef6ae3a49c2fd787f5cbd543a8cf74871304ebced8ee44"},"schema_version":"1.0","source":{"id":"2507.00808","kind":"arxiv","version":2}},"canonical_sha256":"41c5774e3aeb263e2ea411349f403b89eacb6fc39fa212d0566dd6ded858fc4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41c5774e3aeb263e2ea411349f403b89eacb6fc39fa212d0566dd6ded858fc4c","first_computed_at":"2026-07-05T11:30:46.200247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:46.200247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aeo/yhUdJBK3XIdCaJ2RtrQHoYdk6ioRFgiZcU4iFRsX1H+QvahHhZ7imUgwigN/EtzdGE29M4cFwc2sWYioAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:46.200768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:596cd23ccdc2a652558f9444a10025f0ac19139211d811c749b1327228830862","sha256:76c865f4949bd0592dbeb17ef463251c322348a3b512c5187ae86376f713aa3f"],"state_sha256":"54dbc9f1d2bdaa43cb242e1d3d349d0bbfee79eac1f67aaaf0b794591bdc45a9"}