{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WIJDL3UOZTTG3Y7EVW7XYW3CYI","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":"62ce02c5d5d103d13da580137ce07222001bfd5a7cf92af46056e8e60fc85f1c","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-02T09:48:46Z","title_canon_sha256":"a9ecc4bf12119b7d3144b3a76169d659a2383b0fa48e49739adb003aef080deb"},"schema_version":"1.0","source":{"id":"2309.00883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00883","created_at":"2026-07-05T06:47:29Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00883v1","created_at":"2026-07-05T06:47:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00883","created_at":"2026-07-05T06:47:29Z"},{"alias_kind":"pith_short_12","alias_value":"WIJDL3UOZTTG","created_at":"2026-07-05T06:47:29Z"},{"alias_kind":"pith_short_16","alias_value":"WIJDL3UOZTTG3Y7E","created_at":"2026-07-05T06:47:29Z"},{"alias_kind":"pith_short_8","alias_value":"WIJDL3UO","created_at":"2026-07-05T06:47:29Z"}],"graph_snapshots":[{"event_id":"sha256:c7f5edabbdc326dcd7d76e66ae8a091e03157ace8cec8890596d2d16745a7399","target":"graph","created_at":"2026-07-05T06:47:29Z","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/2309.00883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the performance of cross-lingual TTS based on monolingual corpora has been significantly improved recently, generating cross-lingual speech still suffers from the foreign accent problem, leading to limited naturalness. Besides, current cross-lingual methods ignore modeling emotion, which is indispensable paralinguistic information in speech delivery. In this paper, we propose DiCLET-TTS, a Diffusion model based Cross-Lingual Emotion Transfer method that can transfer emotion from a source speaker to the intra- and cross-lingual target speakers. Specifically, to relieve the foreign accent ","authors_text":"Chenxu Hu, Jian Cong, Jingbei Li, Lei Xie, Qiao Tian, Tao Li, Xinfa Zhu, Yuping Wang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-02T09:48:46Z","title":"DiCLET-TTS: Diffusion Model based Cross-lingual Emotion Transfer for Text-to-Speech -- A Study between English and Mandarin"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00883","kind":"arxiv","version":1},"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":"sha256:9e117112cb05aefc3d220ab5a22fafd42274a0a3fe67d23a4fb8832c2538c702","target":"record","created_at":"2026-07-05T06:47:29Z","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":"62ce02c5d5d103d13da580137ce07222001bfd5a7cf92af46056e8e60fc85f1c","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-02T09:48:46Z","title_canon_sha256":"a9ecc4bf12119b7d3144b3a76169d659a2383b0fa48e49739adb003aef080deb"},"schema_version":"1.0","source":{"id":"2309.00883","kind":"arxiv","version":1}},"canonical_sha256":"b21235ee8ecce66de3e4adbf7c5b62c21891adcbfd498e007213b55baff6084d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b21235ee8ecce66de3e4adbf7c5b62c21891adcbfd498e007213b55baff6084d","first_computed_at":"2026-07-05T06:47:29.227195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:29.227195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zbbsitKkvg7SR/BDNyM6z8+3lDXCldkT7ysWo4dQEdm08jtVeT65slr5IA/605zfMBjytuWTSYEVy0FNBFk9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:29.227684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e117112cb05aefc3d220ab5a22fafd42274a0a3fe67d23a4fb8832c2538c702","sha256:c7f5edabbdc326dcd7d76e66ae8a091e03157ace8cec8890596d2d16745a7399"],"state_sha256":"434d10611085cf83e64ca9c61070364dd3c21256842bedf755a804639ce32f5e"}