{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F6PUKEMD74MMFI2GLRLWZBGSR2","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":"e1c20c9ae5b758ddd64ad2a326610a02bb09097bf56197e8e1c6153805b06943","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T05:07:06Z","title_canon_sha256":"f5f25ae960aaddea843a9b604f6acac64c39ef86b234e577477ff6a687a626db"},"schema_version":"1.0","source":{"id":"2506.01322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01322","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01322v1","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01322","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"F6PUKEMD74MM","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"F6PUKEMD74MMFI2G","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"F6PUKEMD","created_at":"2026-07-05T11:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:1e7961fd26aa8e07dec2bbc22f9cd47686fa79e947a83f31f9402c6969d03d65","target":"graph","created_at":"2026-07-05T11:14:11Z","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/2506.01322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces PhoAudiobook, a newly curated dataset comprising 941 hours of high-quality audio for Vietnamese text-to-speech. Using PhoAudiobook, we conduct experiments on three leading zero-shot TTS models: VALL-E, VoiceCraft, and XTTS-V2. Our findings demonstrate that PhoAudiobook consistently enhances model performance across various metrics. Moreover, VALL-E and VoiceCraft exhibit superior performance in synthesizing short sentences, highlighting their robustness in handling diverse linguistic contexts. We publicly release PhoAudiobook to facilitate further research and development","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Thi Vu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T05:07:06Z","title":"Zero-Shot Text-to-Speech for Vietnamese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01322","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":"sha256:144928d47e134149421e67ae69e8a04b603583b4b2ada0828fbe2408df16fef3","target":"record","created_at":"2026-07-05T11:14:11Z","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":"e1c20c9ae5b758ddd64ad2a326610a02bb09097bf56197e8e1c6153805b06943","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T05:07:06Z","title_canon_sha256":"f5f25ae960aaddea843a9b604f6acac64c39ef86b234e577477ff6a687a626db"},"schema_version":"1.0","source":{"id":"2506.01322","kind":"arxiv","version":1}},"canonical_sha256":"2f9f451183ff18c2a3465c576c84d28e88e9899ec12200c23c8bf81ec3c20f37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f9f451183ff18c2a3465c576c84d28e88e9899ec12200c23c8bf81ec3c20f37","first_computed_at":"2026-07-05T11:14:11.710680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:11.710680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lo9GyCxga+uVzPvcU1hXW1NTdpme2R8B4Rcl6VbN6c/i623HNZtz0kRLFMDieVtAF8hcMAy6j+4XYcgwZKNPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:11.711142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:144928d47e134149421e67ae69e8a04b603583b4b2ada0828fbe2408df16fef3","sha256:1e7961fd26aa8e07dec2bbc22f9cd47686fa79e947a83f31f9402c6969d03d65"],"state_sha256":"e3ab4c0186d2841951ca89f5529b51626bdca74820b3622ae204bc31751724a8"}