{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3S3OT74LXNNFMAGDME7YFTIZ43","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":"1aadc6cf799d90cdcec2caa172efca582d790129b7c55ababdd1b04e9cf309e9","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T11:22:08Z","title_canon_sha256":"8333f0c545e6e1521be23d1e71ab1cdf4ad03ae1f506ee4fe2cc2e6a5b8719e9"},"schema_version":"1.0","source":{"id":"2507.04349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04349","created_at":"2026-07-05T11:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04349v1","created_at":"2026-07-05T11:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04349","created_at":"2026-07-05T11:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"3S3OT74LXNNF","created_at":"2026-07-05T11:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"3S3OT74LXNNFMAGD","created_at":"2026-07-05T11:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"3S3OT74L","created_at":"2026-07-05T11:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:190c25f50d4b5818f49ba726601f4b36800119ac45c816a88cc22c8b0ac84d1d","target":"graph","created_at":"2026-07-05T11:33:06Z","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/2507.04349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in text-to-speech (TTS) have enabled natural speech synthesis, but fine-grained, time-varying emotion control remains challenging. Existing methods often allow only utterance-level control and require full model fine-tuning with a large emotion speech dataset, which can degrade performance. Inspired by adding conditional control to the existing model in ControlNet (Zhang et al, 2023), we propose the first ControlNet-based approach for controllable flow-matching TTS (TTS-CtrlNet), which freezes the original model and introduces a trainable copy of it to process additional condit","authors_text":"Jaeseok Jeong, Mingi Kwon, Youngjung Uh, Yuna Lee","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T11:22:08Z","title":"TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with ControlNet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04349","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":"sha256:7de31c52adc23815d810758295c16e06791e3e724e823a1181030cc381949de4","target":"record","created_at":"2026-07-05T11:33:06Z","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":"1aadc6cf799d90cdcec2caa172efca582d790129b7c55ababdd1b04e9cf309e9","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-06T11:22:08Z","title_canon_sha256":"8333f0c545e6e1521be23d1e71ab1cdf4ad03ae1f506ee4fe2cc2e6a5b8719e9"},"schema_version":"1.0","source":{"id":"2507.04349","kind":"arxiv","version":1}},"canonical_sha256":"dcb6e9ff8bbb5a5600c3613f82cd19e6f39eb7715b15ed82073cb24248f4f6fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcb6e9ff8bbb5a5600c3613f82cd19e6f39eb7715b15ed82073cb24248f4f6fd","first_computed_at":"2026-07-05T11:33:06.285530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:06.285530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z0ac0i+Crk7FsNwceQXw89KXqgnJCYSrjPkCB1y/NqOKLjaU6XtK116g8DjT41U5uRo6iz1L2YYcEeDpr4dsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:06.286155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7de31c52adc23815d810758295c16e06791e3e724e823a1181030cc381949de4","sha256:190c25f50d4b5818f49ba726601f4b36800119ac45c816a88cc22c8b0ac84d1d"],"state_sha256":"2d34f1d63320320e14d8f98b7099d60edc8c716d2a346864b1a10c8e0911f456"}