{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROLZ37M5HCVU56ACQ6BLLNOEQA","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":"923cc43dfedd2d990517db0e4734227bf26d62bf98732d3bb13cb789c386edc8","cross_cats_sorted":["cs.AI","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T00:54:15Z","title_canon_sha256":"6bbc5effd085c3d834f18f7497c4b203da8f59a5d2b41a85966fce761db6ab24"},"schema_version":"1.0","source":{"id":"2407.12229","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12229","created_at":"2026-07-05T09:07:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12229v2","created_at":"2026-07-05T09:07:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12229","created_at":"2026-07-05T09:07:49Z"},{"alias_kind":"pith_short_12","alias_value":"ROLZ37M5HCVU","created_at":"2026-07-05T09:07:49Z"},{"alias_kind":"pith_short_16","alias_value":"ROLZ37M5HCVU56AC","created_at":"2026-07-05T09:07:49Z"},{"alias_kind":"pith_short_8","alias_value":"ROLZ37M5","created_at":"2026-07-05T09:07:49Z"}],"graph_snapshots":[{"event_id":"sha256:2b9a8e96aa6000093e3dcea6398f5eec5b115dc16a2e77b566302190d8bcfeee","target":"graph","created_at":"2026-07-05T09:07:49Z","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/2407.12229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"People change their tones of voice, often accompanied by nonverbal vocalizations (NVs) such as laughter and cries, to convey rich emotions. However, most text-to-speech (TTS) systems lack the capability to generate speech with rich emotions, including NVs. This paper introduces EmoCtrl-TTS, an emotion-controllable zero-shot TTS that can generate highly emotional speech with NVs for any speaker. EmoCtrl-TTS leverages arousal and valence values, as well as laughter embeddings, to condition the flow-matching-based zero-shot TTS. To achieve high-quality emotional speech generation, EmoCtrl-TTS is ","authors_text":"Canrun Li, Chung-Hsien Tsai, Daniel Tompkins, Haibin Wu, Jinyu Li, Manthan Thakker, Naoyuki Kanda, Sefik Emre Eskimez, Sheng Zhao, Xiaofei Wang, Zhen Xiao","cross_cats":["cs.AI","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T00:54:15Z","title":"Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12229","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:f4ed0f43bd03db5d1965341dedacfb06a032fd76f48bb043b0526b168f3ba695","target":"record","created_at":"2026-07-05T09:07:49Z","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":"923cc43dfedd2d990517db0e4734227bf26d62bf98732d3bb13cb789c386edc8","cross_cats_sorted":["cs.AI","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T00:54:15Z","title_canon_sha256":"6bbc5effd085c3d834f18f7497c4b203da8f59a5d2b41a85966fce761db6ab24"},"schema_version":"1.0","source":{"id":"2407.12229","kind":"arxiv","version":2}},"canonical_sha256":"8b979dfd9d38ab4ef8028782b5b5c48018586e5b5a62235f520608d9a0e46499","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b979dfd9d38ab4ef8028782b5b5c48018586e5b5a62235f520608d9a0e46499","first_computed_at":"2026-07-05T09:07:49.966044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:49.966044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67eosnqMZYXhMiCrMPGHPxsySGcid88X+KdAUyVwVMA+CopPlV+Q6rjOpik3VW/D2QId2Tn+jJTan9myFvRADg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:49.966582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12229","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4ed0f43bd03db5d1965341dedacfb06a032fd76f48bb043b0526b168f3ba695","sha256:2b9a8e96aa6000093e3dcea6398f5eec5b115dc16a2e77b566302190d8bcfeee"],"state_sha256":"7741efc96614e2655535267aad8e6e6ffc41eff39b97a810956cb9b3c4257278"}