{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S475O2KYDOTNHP3AVDDH4UVTMJ","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":"cf1b83bef4e2b31ed424f6854faadde19cb393df3fdb58608b4ec92a40a24962","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T03:19:39Z","title_canon_sha256":"711cde4436c989ecdb65bcd8b3331e7d9d93f8a1f0d509930814c53f1afdf87c"},"schema_version":"1.0","source":{"id":"2404.18398","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18398","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18398v2","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18398","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"S475O2KYDOTN","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"S475O2KYDOTNHP3A","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"S475O2KY","created_at":"2026-07-05T10:16:33Z"}],"graph_snapshots":[{"event_id":"sha256:74f892d0b967aab79e8bb2e5f3eb0e64654110a6f017db010e6b23926eb9c2ad","target":"graph","created_at":"2026-07-05T10:16:33Z","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/2404.18398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotional Text-to-Speech (E-TTS) synthesis has garnered significant attention in recent years due to its potential to revolutionize human-computer interaction. However, current E-TTS approaches often struggle to capture the intricacies of human emotions, primarily relying on oversimplified emotional labels or single-modality input. In this paper, we introduce the Unified Multimodal Prompt-Induced Emotional Text-to-Speech System (UMETTS), a novel framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech. The core of UMETTS con","authors_text":"Alexander G. Hauptmann, Jun-Yan He, Junyao Chen, Xiang Li, Xiaojiang Peng, Xiaomao Fan, Zhi-Qi Cheng","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T03:19:39Z","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18398","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:ff2e241672e74a324eaadbf18df5a33d0862e0362099231ed9ded2b42f8174c4","target":"record","created_at":"2026-07-05T10:16:33Z","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":"cf1b83bef4e2b31ed424f6854faadde19cb393df3fdb58608b4ec92a40a24962","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T03:19:39Z","title_canon_sha256":"711cde4436c989ecdb65bcd8b3331e7d9d93f8a1f0d509930814c53f1afdf87c"},"schema_version":"1.0","source":{"id":"2404.18398","kind":"arxiv","version":2}},"canonical_sha256":"973fd769581ba6d3bf60a8c67e52b36273f1257b6a8286ef2244912e6b1d8dbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"973fd769581ba6d3bf60a8c67e52b36273f1257b6a8286ef2244912e6b1d8dbd","first_computed_at":"2026-07-05T10:16:33.488189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:33.488189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EMHJO6g4HysVjbXQVXfcWAQivVD+i/kGhFNiz2UDmyTezXJlMYyTbatlSm4MhwRc02HamQVFieJ/mdgJ2ll3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:33.488682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18398","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff2e241672e74a324eaadbf18df5a33d0862e0362099231ed9ded2b42f8174c4","sha256:74f892d0b967aab79e8bb2e5f3eb0e64654110a6f017db010e6b23926eb9c2ad"],"state_sha256":"2cac63fe4f14484bbb9dda1abc69925e338b329373b53220274d76c1ef133662"}