{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XNA3ITEW22Z7T3DCTQVS35SI3J","short_pith_number":"pith:XNA3ITEW","schema_version":"1.0","canonical_sha256":"bb41b44c96d6b3f9ec629c2b2df648da6ae10dc82bb0f3cfb795a3975fab4274","source":{"kind":"arxiv","id":"2504.12867","version":4},"attestation_state":"computed","paper":{"title":"EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","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","submitted_at":"2025-04-17T11:50:04Z","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"},"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":"2504.12867","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-04-17T11:50:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ccd11b36e3ab057c9e994d4457ddbc0868de3d297170e4a588ce4b8a586e4c49","abstract_canon_sha256":"4dec9eebabc9d3e1f52017f7044d54fe58995d6281251fc2fb1b420f4a791c16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:01.969083Z","signature_b64":"75kutUfrNF+rbJ+uK54SzqxMoXFtltAWAX33d1OmVDG3nrtxSYS6Zn2bKXwFkfmnTihSB9y7Lj+XNr6WgleNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb41b44c96d6b3f9ec629c2b2df648da6ae10dc82bb0f3cfb795a3975fab4274","last_reissued_at":"2026-07-05T11:53:01.968615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:01.968615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","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","submitted_at":"2025-04-17T11:50:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12867","kind":"arxiv","version":4},"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/2504.12867/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":"2504.12867","created_at":"2026-07-05T11:53:01.968673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12867v4","created_at":"2026-07-05T11:53:01.968673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12867","created_at":"2026-07-05T11:53:01.968673+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNA3ITEW22Z7","created_at":"2026-07-05T11:53:01.968673+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNA3ITEW22Z7T3DC","created_at":"2026-07-05T11:53:01.968673+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNA3ITEW","created_at":"2026-07-05T11:53:01.968673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19209","citing_title":"FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20650","citing_title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08709","citing_title":"Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J","json":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J.json","graph_json":"https://pith.science/api/pith-number/XNA3ITEW22Z7T3DCTQVS35SI3J/graph.json","events_json":"https://pith.science/api/pith-number/XNA3ITEW22Z7T3DCTQVS35SI3J/events.json","paper":"https://pith.science/paper/XNA3ITEW"},"agent_actions":{"view_html":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J","download_json":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J.json","view_paper":"https://pith.science/paper/XNA3ITEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12867&json=true","fetch_graph":"https://pith.science/api/pith-number/XNA3ITEW22Z7T3DCTQVS35SI3J/graph.json","fetch_events":"https://pith.science/api/pith-number/XNA3ITEW22Z7T3DCTQVS35SI3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J/action/storage_attestation","attest_author":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J/action/author_attestation","sign_citation":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J/action/citation_signature","submit_replication":"https://pith.science/pith/XNA3ITEW22Z7T3DCTQVS35SI3J/action/replication_record"}},"created_at":"2026-07-05T11:53:01.968673+00:00","updated_at":"2026-07-05T11:53:01.968673+00:00"}