{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3LJZPBPGONPZXD5UTMUT3PEHDK","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":"62cbcecfe6c228bc5ec713533dcf144a185f6e3f9d1b806eb13d123bbf700148","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-17T03:02:05Z","title_canon_sha256":"e09bec400808b2e8d8a4992236f255b678789b717d413398d62d767ec8a661c9"},"schema_version":"1.0","source":{"id":"2412.12498","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12498","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12498v3","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12498","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_12","alias_value":"3LJZPBPGONPZ","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_16","alias_value":"3LJZPBPGONPZXD5U","created_at":"2026-07-05T11:25:06Z"},{"alias_kind":"pith_short_8","alias_value":"3LJZPBPG","created_at":"2026-07-05T11:25:06Z"}],"graph_snapshots":[{"event_id":"sha256:3edc26848aa85843d71096d95294101e2fceb14bbe67bdd610ae189a4475f5c1","target":"graph","created_at":"2026-07-05T11:25:06Z","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/2412.12498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotional text-to-speech synthesis (TTS) aims to generate realistic emotional speech from input text. However, quantitatively controlling multi-level emotion rendering remains challenging. In this paper, we propose a flow-matching based emotional TTS framework with a novel approach for emotion intensity modeling to facilitate fine-grained control over emotion rendering at the phoneme, word, and utterance levels. We introduce a hierarchical emotion distribution (ED) extractor that captures a quantifiable ED embedding across different speech segment levels. Additionally, we explore various acous","authors_text":"Haizhou Li, Kun Zhou, Sho Inoue, Shuai Wang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-17T03:02:05Z","title":"Hierarchical Control of Emotion Rendering in Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12498","kind":"arxiv","version":3},"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":"sha256:9d48e83d9df0e3693a90bf18570011e1f00c5434f013a6869721f32c3532c72e","target":"record","created_at":"2026-07-05T11:25:06Z","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":"62cbcecfe6c228bc5ec713533dcf144a185f6e3f9d1b806eb13d123bbf700148","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-17T03:02:05Z","title_canon_sha256":"e09bec400808b2e8d8a4992236f255b678789b717d413398d62d767ec8a661c9"},"schema_version":"1.0","source":{"id":"2412.12498","kind":"arxiv","version":3}},"canonical_sha256":"dad39785e6735f9b8fb49b293dbc871abc67bcf5337b8256ff56047c2c83a0a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad39785e6735f9b8fb49b293dbc871abc67bcf5337b8256ff56047c2c83a0a9","first_computed_at":"2026-07-05T11:25:06.548078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:06.548078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+C3WSswo4zgwByGSosC0+LQNUhOul2657o2Ei2BC6GrLMxC+7Ow7vWtNjyhGc6eWhNLSjvPz5Xt0pEJ4KSFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:06.548953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12498","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d48e83d9df0e3693a90bf18570011e1f00c5434f013a6869721f32c3532c72e","sha256:3edc26848aa85843d71096d95294101e2fceb14bbe67bdd610ae189a4475f5c1"],"state_sha256":"ca47a9d8bd1a25b7fd480121bc69930ca59d6dd676a107d310947b8b8602a524"}