{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S475O2KYDOTNHP3AVDDH4UVTMJ","short_pith_number":"pith:S475O2KY","canonical_record":{"source":{"id":"2404.18398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T03:19:39Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"711cde4436c989ecdb65bcd8b3331e7d9d93f8a1f0d509930814c53f1afdf87c","abstract_canon_sha256":"cf1b83bef4e2b31ed424f6854faadde19cb393df3fdb58608b4ec92a40a24962"},"schema_version":"1.0"},"canonical_sha256":"973fd769581ba6d3bf60a8c67e52b36273f1257b6a8286ef2244912e6b1d8dbd","source":{"kind":"arxiv","id":"2404.18398","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S475O2KYDOTNHP3AVDDH4UVTMJ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T03:19:39Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"711cde4436c989ecdb65bcd8b3331e7d9d93f8a1f0d509930814c53f1afdf87c","abstract_canon_sha256":"cf1b83bef4e2b31ed424f6854faadde19cb393df3fdb58608b4ec92a40a24962"},"schema_version":"1.0"},"canonical_sha256":"973fd769581ba6d3bf60a8c67e52b36273f1257b6a8286ef2244912e6b1d8dbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:33.488682Z","signature_b64":"EMHJO6g4HysVjbXQVXfcWAQivVD+i/kGhFNiz2UDmyTezXJlMYyTbatlSm4MhwRc02HamQVFieJ/mdgJ2ll3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"973fd769581ba6d3bf60a8c67e52b36273f1257b6a8286ef2244912e6b1d8dbd","last_reissued_at":"2026-07-05T10:16:33.488189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:33.488189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18398","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wjP4ohOYTmuKW37iS/77SIIP45qgCsRQjZQWX6+Mdqn88TeyQKghLdNKGmagtYfaU1zb3vFGCStYTEXJYx/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:58:41.391866Z"},"content_sha256":"ff2e241672e74a324eaadbf18df5a33d0862e0362099231ed9ded2b42f8174c4","schema_version":"1.0","event_id":"sha256:ff2e241672e74a324eaadbf18df5a33d0862e0362099231ed9ded2b42f8174c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S475O2KYDOTNHP3AVDDH4UVTMJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CL","authors_text":"Alexander G. Hauptmann, Jun-Yan He, Junyao Chen, Xiang Li, Xiaojiang Peng, Xiaomao Fan, Zhi-Qi Cheng","submitted_at":"2024-04-29T03:19:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18398","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/2404.18398/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxy167JjSYK3/hjYiESAsdPxWfcICS7ixFpFa5KVB3U+TahSbLaZR5zlK8vvU8vBy8NmZFe2g7e1b6oid1YYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:58:41.392829Z"},"content_sha256":"74f892d0b967aab79e8bb2e5f3eb0e64654110a6f017db010e6b23926eb9c2ad","schema_version":"1.0","event_id":"sha256:74f892d0b967aab79e8bb2e5f3eb0e64654110a6f017db010e6b23926eb9c2ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S475O2KYDOTNHP3AVDDH4UVTMJ/bundle.json","state_url":"https://pith.science/pith/S475O2KYDOTNHP3AVDDH4UVTMJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S475O2KYDOTNHP3AVDDH4UVTMJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T04:58:41Z","links":{"resolver":"https://pith.science/pith/S475O2KYDOTNHP3AVDDH4UVTMJ","bundle":"https://pith.science/pith/S475O2KYDOTNHP3AVDDH4UVTMJ/bundle.json","state":"https://pith.science/pith/S475O2KYDOTNHP3AVDDH4UVTMJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S475O2KYDOTNHP3AVDDH4UVTMJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nnPFTsfkr1tG3HJ/kHTHyAbwRNCfcofbdS0kdHWpqAcJUeSXVMVbPHozSciQKa2Gmp8rwHoqMt7MJZz7FqVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:58:41.399233Z","bundle_sha256":"84e2e2aae338b3fd465bd2af48df1a6b0b4ea16384392e847b661764e5daea07"}}