{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MFHSSBTWXMC2RKAQLRGIMJWBUH","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":"7e70bf3aab13aff2b46151b945f32fbae80c1155f841a43c22338bff3b3f90ca","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T17:31:26Z","title_canon_sha256":"6020f8e46486dc27b3c2bc26d38e98d4eb01a3d4283ebffd1cdf332073b60499"},"schema_version":"1.0","source":{"id":"2501.17790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17790","created_at":"2026-07-05T10:06:57Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17790v1","created_at":"2026-07-05T10:06:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17790","created_at":"2026-07-05T10:06:57Z"},{"alias_kind":"pith_short_12","alias_value":"MFHSSBTWXMC2","created_at":"2026-07-05T10:06:57Z"},{"alias_kind":"pith_short_16","alias_value":"MFHSSBTWXMC2RKAQ","created_at":"2026-07-05T10:06:57Z"},{"alias_kind":"pith_short_8","alias_value":"MFHSSBTW","created_at":"2026-07-05T10:06:57Z"}],"graph_snapshots":[{"event_id":"sha256:cb306f223687d49847c7a6f1cc2defc9884e5ed8b8e42af4b0f7bd2d4b1aefae","target":"graph","created_at":"2026-07-05T10:06:57Z","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/2501.17790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyphone disambiguation in the language. Building upon CosyVoice, we incorporate a $S^{3}$ tokenizer, a large language model (LLM), an optimal-transport conditional flow matching model (OT-CFM), and a grapheme to phoneme prediction model, to generate realistic speech that closely mimics human utterances. Our evaluation demonstrates BreezyVoice's superior performance in both general and code-switching contexts, highlighti","authors_text":"Chan-Jan Hsu, Chen-An Li, Chia-Chun Lin, Chien-Cheng Chen, Chien-Yu Yu, Da-shan Shiu, Ho Lam Chung, Hung-yi Lee, Ming-Ji Lee, Ru-Heng Huang, Wei-Chih Chen, Yi-Chang Chen, Yi-Cheng Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T17:31:26Z","title":"BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17790","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":"sha256:972c7a418beb1811042f343ef4da3af45e944b744ad7d0cd5d07ae1d530768ec","target":"record","created_at":"2026-07-05T10:06:57Z","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":"7e70bf3aab13aff2b46151b945f32fbae80c1155f841a43c22338bff3b3f90ca","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T17:31:26Z","title_canon_sha256":"6020f8e46486dc27b3c2bc26d38e98d4eb01a3d4283ebffd1cdf332073b60499"},"schema_version":"1.0","source":{"id":"2501.17790","kind":"arxiv","version":1}},"canonical_sha256":"614f290676bb05a8a8105c4c8626c1a1c3b1c3ac5c59b856c81deaaac60d0750","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"614f290676bb05a8a8105c4c8626c1a1c3b1c3ac5c59b856c81deaaac60d0750","first_computed_at":"2026-07-05T10:06:57.904363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:57.904363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3uV66UlVRdTksqODrwGN76qB6m9dhDL6sh/10QD+Aip/KgtrqgWBwHhbLSQfLn0Mc3fS3yAkqhfWKn+Zh3NvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:57.904816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:972c7a418beb1811042f343ef4da3af45e944b744ad7d0cd5d07ae1d530768ec","sha256:cb306f223687d49847c7a6f1cc2defc9884e5ed8b8e42af4b0f7bd2d4b1aefae"],"state_sha256":"0c4b2404eb371b9bb475585b9f9140ea54206b0d1aff1b921420ce5734459f4b"}