{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XNA3ITEW22Z7T3DCTQVS35SI3J","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":"4dec9eebabc9d3e1f52017f7044d54fe58995d6281251fc2fb1b420f4a791c16","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-04-17T11:50:04Z","title_canon_sha256":"ccd11b36e3ab057c9e994d4457ddbc0868de3d297170e4a588ce4b8a586e4c49"},"schema_version":"1.0","source":{"id":"2504.12867","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12867","created_at":"2026-07-05T11:53:01Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12867v4","created_at":"2026-07-05T11:53:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12867","created_at":"2026-07-05T11:53:01Z"},{"alias_kind":"pith_short_12","alias_value":"XNA3ITEW22Z7","created_at":"2026-07-05T11:53:01Z"},{"alias_kind":"pith_short_16","alias_value":"XNA3ITEW22Z7T3DC","created_at":"2026-07-05T11:53:01Z"},{"alias_kind":"pith_short_8","alias_value":"XNA3ITEW","created_at":"2026-07-05T11:53:01Z"}],"graph_snapshots":[{"event_id":"sha256:62c69a3e0e4010c9d1e36ae85c6f8f3d38ffdfbb11d4096eabc80a5318d44bb1","target":"graph","created_at":"2026-07-05T11:53:01Z","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/2504.12867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human speech goes beyond the mere transfer of information; it is a profound exchange of emotions and a connection between individuals. While Text-to-Speech (TTS) models have made huge progress, they still face challenges in controlling the emotional expression in the generated speech. In this work, we propose EmoVoice, a novel emotion-controllable TTS model that exploits large language models (LLMs) to enable fine-grained freestyle natural language emotion control, and a phoneme boost variant design that makes the model output phoneme tokens and audio tokens in parallel to enhance content cons","authors_text":"Chen Yang, Fan Yu, Guanrou Yang, Qian Chen, Shiliang Zhang, Tianrui Wang, Wenrui Liu, Wen Wang, Wenxi Chen, Xie Chen, Yifan Yang, Zhifu Gao, Zhihao Du, Zhikang Niu, Ziyang Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-04-17T11:50:04Z","title":"EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12867","kind":"arxiv","version":4},"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":"sha256:5be78452e8b1f38e6faeb3128c820306353c53cf6dabac19ae3b72148e3bdb3b","target":"record","created_at":"2026-07-05T11:53:01Z","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":"4dec9eebabc9d3e1f52017f7044d54fe58995d6281251fc2fb1b420f4a791c16","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-04-17T11:50:04Z","title_canon_sha256":"ccd11b36e3ab057c9e994d4457ddbc0868de3d297170e4a588ce4b8a586e4c49"},"schema_version":"1.0","source":{"id":"2504.12867","kind":"arxiv","version":4}},"canonical_sha256":"bb41b44c96d6b3f9ec629c2b2df648da6ae10dc82bb0f3cfb795a3975fab4274","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb41b44c96d6b3f9ec629c2b2df648da6ae10dc82bb0f3cfb795a3975fab4274","first_computed_at":"2026-07-05T11:53:01.968615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:01.968615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"75kutUfrNF+rbJ+uK54SzqxMoXFtltAWAX33d1OmVDG3nrtxSYS6Zn2bKXwFkfmnTihSB9y7Lj+XNr6WgleNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:01.969083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12867","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5be78452e8b1f38e6faeb3128c820306353c53cf6dabac19ae3b72148e3bdb3b","sha256:62c69a3e0e4010c9d1e36ae85c6f8f3d38ffdfbb11d4096eabc80a5318d44bb1"],"state_sha256":"eec78ce3b768aba528280188cae97f8475d4f671c7f69aa67e0e365420c04d50"}