{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROLZ37M5HCVU56ACQ6BLLNOEQA","short_pith_number":"pith:ROLZ37M5","schema_version":"1.0","canonical_sha256":"8b979dfd9d38ab4ef8028782b5b5c48018586e5b5a62235f520608d9a0e46499","source":{"kind":"arxiv","id":"2407.12229","version":2},"attestation_state":"computed","paper":{"title":"Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"eess.AS","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","submitted_at":"2024-07-17T00:54:15Z","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 "},"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":"2407.12229","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T00:54:15Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"6bbc5effd085c3d834f18f7497c4b203da8f59a5d2b41a85966fce761db6ab24","abstract_canon_sha256":"923cc43dfedd2d990517db0e4734227bf26d62bf98732d3bb13cb789c386edc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:49.966582Z","signature_b64":"67eosnqMZYXhMiCrMPGHPxsySGcid88X+KdAUyVwVMA+CopPlV+Q6rjOpik3VW/D2QId2Tn+jJTan9myFvRADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b979dfd9d38ab4ef8028782b5b5c48018586e5b5a62235f520608d9a0e46499","last_reissued_at":"2026-07-05T09:07:49.966044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:49.966044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"eess.AS","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","submitted_at":"2024-07-17T00:54:15Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12229","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/2407.12229/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":"2407.12229","created_at":"2026-07-05T09:07:49.966121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12229v2","created_at":"2026-07-05T09:07:49.966121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12229","created_at":"2026-07-05T09:07:49.966121+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROLZ37M5HCVU","created_at":"2026-07-05T09:07:49.966121+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROLZ37M5HCVU56AC","created_at":"2026-07-05T09:07:49.966121+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROLZ37M5","created_at":"2026-07-05T09:07:49.966121+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/ROLZ37M5HCVU56ACQ6BLLNOEQA","json":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA.json","graph_json":"https://pith.science/api/pith-number/ROLZ37M5HCVU56ACQ6BLLNOEQA/graph.json","events_json":"https://pith.science/api/pith-number/ROLZ37M5HCVU56ACQ6BLLNOEQA/events.json","paper":"https://pith.science/paper/ROLZ37M5"},"agent_actions":{"view_html":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA","download_json":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA.json","view_paper":"https://pith.science/paper/ROLZ37M5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12229&json=true","fetch_graph":"https://pith.science/api/pith-number/ROLZ37M5HCVU56ACQ6BLLNOEQA/graph.json","fetch_events":"https://pith.science/api/pith-number/ROLZ37M5HCVU56ACQ6BLLNOEQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA/action/storage_attestation","attest_author":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA/action/author_attestation","sign_citation":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA/action/citation_signature","submit_replication":"https://pith.science/pith/ROLZ37M5HCVU56ACQ6BLLNOEQA/action/replication_record"}},"created_at":"2026-07-05T09:07:49.966121+00:00","updated_at":"2026-07-05T09:07:49.966121+00:00"}