{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RSYUOVWXAMEV52EDPTOFQGA632","short_pith_number":"pith:RSYUOVWX","schema_version":"1.0","canonical_sha256":"8cb14756d703095ee8837cdc58181edeadfba9f052f85666bbbe388e14935d52","source":{"kind":"arxiv","id":"2505.18453","version":1},"attestation_state":"computed","paper":{"title":"MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Long Ma, Qiulin Li, Qun Yang, Songjun Cao, Yueteng Kang, Zhichao Wu","submitted_at":"2025-05-24T01:26:02Z","abstract_excerpt":"Most existing Zero-Shot Text-To-Speech(ZS-TTS) systems generate the unseen speech based on single prompt, such as reference speech or text descriptions, which limits their flexibility. We propose a customized emotion ZS-TTS system based on multi-modal prompt. The system disentangles speech into the content, timbre, emotion and prosody, allowing emotion prompts to be provided as text, image or speech. To extract emotion information from different prompts, we propose a multi-modal prompt emotion encoder. Additionally, we introduce an prosody predictor to fit the distribution of prosody and propo"},"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":"2505.18453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-24T01:26:02Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"75eff6988ce694a3efbd8ab34bd7963d8126294231b4d5d14a1345f5b0a274e2","abstract_canon_sha256":"48765892fa885788b72bc282c77d59898166a05b5a0bfa1250b1f30f00f2e3ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:46.685879Z","signature_b64":"9gwacXBBBMrMqskQnZ6Ta77F/hKL+ydlX4px+CIWAt5WjBJ6A38J/RPDfqjYIbrp2o626ai+R721vAcdil4PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb14756d703095ee8837cdc58181edeadfba9f052f85666bbbe388e14935d52","last_reissued_at":"2026-07-05T11:08:46.685476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:46.685476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Long Ma, Qiulin Li, Qun Yang, Songjun Cao, Yueteng Kang, Zhichao Wu","submitted_at":"2025-05-24T01:26:02Z","abstract_excerpt":"Most existing Zero-Shot Text-To-Speech(ZS-TTS) systems generate the unseen speech based on single prompt, such as reference speech or text descriptions, which limits their flexibility. We propose a customized emotion ZS-TTS system based on multi-modal prompt. The system disentangles speech into the content, timbre, emotion and prosody, allowing emotion prompts to be provided as text, image or speech. To extract emotion information from different prompts, we propose a multi-modal prompt emotion encoder. Additionally, we introduce an prosody predictor to fit the distribution of prosody and propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18453","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/2505.18453/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":"2505.18453","created_at":"2026-07-05T11:08:46.685531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18453v1","created_at":"2026-07-05T11:08:46.685531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18453","created_at":"2026-07-05T11:08:46.685531+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSYUOVWXAMEV","created_at":"2026-07-05T11:08:46.685531+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSYUOVWXAMEV52ED","created_at":"2026-07-05T11:08:46.685531+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSYUOVWX","created_at":"2026-07-05T11:08:46.685531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632","json":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632.json","graph_json":"https://pith.science/api/pith-number/RSYUOVWXAMEV52EDPTOFQGA632/graph.json","events_json":"https://pith.science/api/pith-number/RSYUOVWXAMEV52EDPTOFQGA632/events.json","paper":"https://pith.science/paper/RSYUOVWX"},"agent_actions":{"view_html":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632","download_json":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632.json","view_paper":"https://pith.science/paper/RSYUOVWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18453&json=true","fetch_graph":"https://pith.science/api/pith-number/RSYUOVWXAMEV52EDPTOFQGA632/graph.json","fetch_events":"https://pith.science/api/pith-number/RSYUOVWXAMEV52EDPTOFQGA632/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632/action/storage_attestation","attest_author":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632/action/author_attestation","sign_citation":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632/action/citation_signature","submit_replication":"https://pith.science/pith/RSYUOVWXAMEV52EDPTOFQGA632/action/replication_record"}},"created_at":"2026-07-05T11:08:46.685531+00:00","updated_at":"2026-07-05T11:08:46.685531+00:00"}