{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UERMLUC4YYB2V6XLCOKFITRCCY","short_pith_number":"pith:UERMLUC4","schema_version":"1.0","canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","source":{"kind":"arxiv","id":"2510.10774","version":3},"attestation_state":"computed","paper":{"title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.SD","authors_text":"Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi","submitted_at":"2025-10-12T19:33:11Z","abstract_excerpt":"Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, an"},"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":"2510.10774","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-12T19:33:11Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"8359a9ae44721e2d5a687f0367e319560ad7ff47ada5f89f00e81b1a33d3ef5c","abstract_canon_sha256":"e6b64b31ec03d61a0514846c9369c215355c0aadded808dda5d83f0062c69dd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:38.768110Z","signature_b64":"wy7pQVWTi9KnrXEiHWB6XJ4Wa9D3BvuAthP2ApKhK8vpUc46pCLgmtAsru/l49tl9dPqjfppXyPDd5PXJ0msDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","last_reissued_at":"2026-05-27T01:05:38.767488Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:38.767488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.SD","authors_text":"Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi","submitted_at":"2025-10-12T19:33:11Z","abstract_excerpt":"Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10774","kind":"arxiv","version":3},"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/2510.10774/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":"2510.10774","created_at":"2026-05-27T01:05:38.767540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10774v3","created_at":"2026-05-27T01:05:38.767540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10774","created_at":"2026-05-27T01:05:38.767540+00:00"},{"alias_kind":"pith_short_12","alias_value":"UERMLUC4YYB2","created_at":"2026-05-27T01:05:38.767540+00:00"},{"alias_kind":"pith_short_16","alias_value":"UERMLUC4YYB2V6XL","created_at":"2026-05-27T01:05:38.767540+00:00"},{"alias_kind":"pith_short_8","alias_value":"UERMLUC4","created_at":"2026-05-27T01:05:38.767540+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/UERMLUC4YYB2V6XLCOKFITRCCY","json":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY.json","graph_json":"https://pith.science/api/pith-number/UERMLUC4YYB2V6XLCOKFITRCCY/graph.json","events_json":"https://pith.science/api/pith-number/UERMLUC4YYB2V6XLCOKFITRCCY/events.json","paper":"https://pith.science/paper/UERMLUC4"},"agent_actions":{"view_html":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY","download_json":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY.json","view_paper":"https://pith.science/paper/UERMLUC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10774&json=true","fetch_graph":"https://pith.science/api/pith-number/UERMLUC4YYB2V6XLCOKFITRCCY/graph.json","fetch_events":"https://pith.science/api/pith-number/UERMLUC4YYB2V6XLCOKFITRCCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/action/storage_attestation","attest_author":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/action/author_attestation","sign_citation":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/action/citation_signature","submit_replication":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/action/replication_record"}},"created_at":"2026-05-27T01:05:38.767540+00:00","updated_at":"2026-05-27T01:05:38.767540+00:00"}