{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F6PUKEMD74MMFI2GLRLWZBGSR2","short_pith_number":"pith:F6PUKEMD","schema_version":"1.0","canonical_sha256":"2f9f451183ff18c2a3465c576c84d28e88e9899ec12200c23c8bf81ec3c20f37","source":{"kind":"arxiv","id":"2506.01322","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Text-to-Speech for Vietnamese","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Thi Vu","submitted_at":"2025-06-02T05:07:06Z","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"},"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":"2506.01322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T05:07:06Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f5f25ae960aaddea843a9b604f6acac64c39ef86b234e577477ff6a687a626db","abstract_canon_sha256":"e1c20c9ae5b758ddd64ad2a326610a02bb09097bf56197e8e1c6153805b06943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:11.711142Z","signature_b64":"Lo9GyCxga+uVzPvcU1hXW1NTdpme2R8B4Rcl6VbN6c/i623HNZtz0kRLFMDieVtAF8hcMAy6j+4XYcgwZKNPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9f451183ff18c2a3465c576c84d28e88e9899ec12200c23c8bf81ec3c20f37","last_reissued_at":"2026-07-05T11:14:11.710680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:11.710680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Text-to-Speech for Vietnamese","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Thi Vu","submitted_at":"2025-06-02T05:07:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01322","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/2506.01322/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":"2506.01322","created_at":"2026-07-05T11:14:11.710735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01322v1","created_at":"2026-07-05T11:14:11.710735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01322","created_at":"2026-07-05T11:14:11.710735+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6PUKEMD74MM","created_at":"2026-07-05T11:14:11.710735+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6PUKEMD74MMFI2G","created_at":"2026-07-05T11:14:11.710735+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6PUKEMD","created_at":"2026-07-05T11:14:11.710735+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/F6PUKEMD74MMFI2GLRLWZBGSR2","json":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2.json","graph_json":"https://pith.science/api/pith-number/F6PUKEMD74MMFI2GLRLWZBGSR2/graph.json","events_json":"https://pith.science/api/pith-number/F6PUKEMD74MMFI2GLRLWZBGSR2/events.json","paper":"https://pith.science/paper/F6PUKEMD"},"agent_actions":{"view_html":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2","download_json":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2.json","view_paper":"https://pith.science/paper/F6PUKEMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01322&json=true","fetch_graph":"https://pith.science/api/pith-number/F6PUKEMD74MMFI2GLRLWZBGSR2/graph.json","fetch_events":"https://pith.science/api/pith-number/F6PUKEMD74MMFI2GLRLWZBGSR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2/action/storage_attestation","attest_author":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2/action/author_attestation","sign_citation":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2/action/citation_signature","submit_replication":"https://pith.science/pith/F6PUKEMD74MMFI2GLRLWZBGSR2/action/replication_record"}},"created_at":"2026-07-05T11:14:11.710735+00:00","updated_at":"2026-07-05T11:14:11.710735+00:00"}