{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IHCXOTR25MTD4LVECE2J6QB3RH","short_pith_number":"pith:IHCXOTR2","schema_version":"1.0","canonical_sha256":"41c5774e3aeb263e2ea411349f403b89eacb6fc39fa212d0566dd6ded858fc4c","source":{"kind":"arxiv","id":"2507.00808","version":2},"attestation_state":"computed","paper":{"title":"Multi-interaction TTS toward professional recording reproduction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aya Watanabe, Hiroki Kanagawa, Kenichi Fujita, Yusuke Ijima","submitted_at":"2025-07-01T14:40:51Z","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 "},"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":"2507.00808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-01T14:40:51Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"a22386304372f3d922ef6ae3a49c2fd787f5cbd543a8cf74871304ebced8ee44","abstract_canon_sha256":"de870e36cafe2f41c039b765cd48e30f6cde6d5f968467a8f3b64b47c428ff2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:46.200768Z","signature_b64":"aeo/yhUdJBK3XIdCaJ2RtrQHoYdk6ioRFgiZcU4iFRsX1H+QvahHhZ7imUgwigN/EtzdGE29M4cFwc2sWYioAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c5774e3aeb263e2ea411349f403b89eacb6fc39fa212d0566dd6ded858fc4c","last_reissued_at":"2026-07-05T11:30:46.200247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:46.200247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-interaction TTS toward professional recording reproduction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aya Watanabe, Hiroki Kanagawa, Kenichi Fujita, Yusuke Ijima","submitted_at":"2025-07-01T14:40:51Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00808","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/2507.00808/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":"2507.00808","created_at":"2026-07-05T11:30:46.200306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00808v2","created_at":"2026-07-05T11:30:46.200306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00808","created_at":"2026-07-05T11:30:46.200306+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHCXOTR25MTD","created_at":"2026-07-05T11:30:46.200306+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHCXOTR25MTD4LVE","created_at":"2026-07-05T11:30:46.200306+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHCXOTR2","created_at":"2026-07-05T11:30:46.200306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00808","citing_title":"Multi-interaction TTS toward professional recording reproduction","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH","json":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH.json","graph_json":"https://pith.science/api/pith-number/IHCXOTR25MTD4LVECE2J6QB3RH/graph.json","events_json":"https://pith.science/api/pith-number/IHCXOTR25MTD4LVECE2J6QB3RH/events.json","paper":"https://pith.science/paper/IHCXOTR2"},"agent_actions":{"view_html":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH","download_json":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH.json","view_paper":"https://pith.science/paper/IHCXOTR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00808&json=true","fetch_graph":"https://pith.science/api/pith-number/IHCXOTR25MTD4LVECE2J6QB3RH/graph.json","fetch_events":"https://pith.science/api/pith-number/IHCXOTR25MTD4LVECE2J6QB3RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH/action/storage_attestation","attest_author":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH/action/author_attestation","sign_citation":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH/action/citation_signature","submit_replication":"https://pith.science/pith/IHCXOTR25MTD4LVECE2J6QB3RH/action/replication_record"}},"created_at":"2026-07-05T11:30:46.200306+00:00","updated_at":"2026-07-05T11:30:46.200306+00:00"}