{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V54Z5UGTOYTKQD74PQKNLYTMRH","short_pith_number":"pith:V54Z5UGT","schema_version":"1.0","canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","source":{"kind":"arxiv","id":"2409.10157","version":1},"attestation_state":"computed","paper":{"title":"Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Chen Zhang, Huayun Zhang, Nancy F. Chen, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-09-16T10:41:36Z","abstract_excerpt":"Current emotional text-to-speech (TTS) models predominantly conduct supervised training to learn the conversion from text and desired emotion to its emotional speech, focusing on a single emotion per text-speech pair. These models only learn the correct emotional outputs without fully comprehending other emotion characteristics, which limits their capabilities of capturing the nuances between different emotions. We propose a controllable Emo-DPO approach, which employs direct preference optimization to differentiate subtle emotional nuances between emotions through optimizing towards preferred"},"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":"2409.10157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T10:41:36Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"cd9a2f6fb119be3ded9b101ff45a7f80f09dc89f8eaee29b800c1d3795cddb86","abstract_canon_sha256":"329d6126eab61c3fb033d649bbac44fbfde532b8dce0c0d36f7bca4d6de271e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:36.011122Z","signature_b64":"DgCpjKTZYsAU2bLP8ygUh6pOl3begLjhunJnD8RuRYhpUWCLM5MgtPOFDz5ARIxhd3KwMi5cOmiL3COwGBHDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","last_reissued_at":"2026-07-05T09:07:36.010666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:36.010666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Chen Zhang, Huayun Zhang, Nancy F. Chen, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-09-16T10:41:36Z","abstract_excerpt":"Current emotional text-to-speech (TTS) models predominantly conduct supervised training to learn the conversion from text and desired emotion to its emotional speech, focusing on a single emotion per text-speech pair. These models only learn the correct emotional outputs without fully comprehending other emotion characteristics, which limits their capabilities of capturing the nuances between different emotions. We propose a controllable Emo-DPO approach, which employs direct preference optimization to differentiate subtle emotional nuances between emotions through optimizing towards preferred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10157","kind":"arxiv","version":1},"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/2409.10157/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":"2409.10157","created_at":"2026-07-05T09:07:36.010723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10157v1","created_at":"2026-07-05T09:07:36.010723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10157","created_at":"2026-07-05T09:07:36.010723+00:00"},{"alias_kind":"pith_short_12","alias_value":"V54Z5UGTOYTK","created_at":"2026-07-05T09:07:36.010723+00:00"},{"alias_kind":"pith_short_16","alias_value":"V54Z5UGTOYTKQD74","created_at":"2026-07-05T09:07:36.010723+00:00"},{"alias_kind":"pith_short_8","alias_value":"V54Z5UGT","created_at":"2026-07-05T09:07:36.010723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08363","citing_title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH","json":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH.json","graph_json":"https://pith.science/api/pith-number/V54Z5UGTOYTKQD74PQKNLYTMRH/graph.json","events_json":"https://pith.science/api/pith-number/V54Z5UGTOYTKQD74PQKNLYTMRH/events.json","paper":"https://pith.science/paper/V54Z5UGT"},"agent_actions":{"view_html":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH","download_json":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH.json","view_paper":"https://pith.science/paper/V54Z5UGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10157&json=true","fetch_graph":"https://pith.science/api/pith-number/V54Z5UGTOYTKQD74PQKNLYTMRH/graph.json","fetch_events":"https://pith.science/api/pith-number/V54Z5UGTOYTKQD74PQKNLYTMRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/action/storage_attestation","attest_author":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/action/author_attestation","sign_citation":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/action/citation_signature","submit_replication":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/action/replication_record"}},"created_at":"2026-07-05T09:07:36.010723+00:00","updated_at":"2026-07-05T09:07:36.010723+00:00"}