{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DS36KDCYV7T5JUDHESOIPU22YF","short_pith_number":"pith:DS36KDCY","schema_version":"1.0","canonical_sha256":"1cb7e50c58afe7d4d067249c87d35ac16072948593e4e73f8581bc21d01a8803","source":{"kind":"arxiv","id":"2505.20506","version":1},"attestation_state":"computed","paper":{"title":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hanan Aldarmaki, Hawau Olamide Toyin, Humaid Alblooshi, Rufael Marew, Samar M. Magdy","submitted_at":"2025-05-26T20:15:15Z","abstract_excerpt":"We introduce ArVoice, a multi-speaker Modern Standard Arabic (MSA) speech corpus with diacritized transcriptions, intended for multi-speaker speech synthesis, and can be useful for other tasks such as speech-based diacritic restoration, voice conversion, and deepfake detection. ArVoice comprises: (1) a new professionally recorded set from six voice talents with diverse demographics, (2) a modified subset of the Arabic Speech Corpus; and (3) high-quality synthetic speech from two commercial systems. The complete corpus consists of a total of 83.52 hours of speech across 11 voices; around 10 hou"},"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":"2505.20506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T20:15:15Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"925c2da40083d3e144489eec4f40da6afb72776eaccd40198ab591752cfa6a73","abstract_canon_sha256":"acf765d6b4e0fd5f3c047075d2721f824936d63a419a228bdaa1ee3e13f65eaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:13.780436Z","signature_b64":"3BNc3fcCRCBcL1i4qw1hTsLR2TupQRaYZ9HzRnHH+PUMyYy2Qzxa3cMNt6HE1+7oVQa2KH2FaIdWP7mSTrfHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cb7e50c58afe7d4d067249c87d35ac16072948593e4e73f8581bc21d01a8803","last_reissued_at":"2026-07-05T11:10:13.779988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:13.779988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hanan Aldarmaki, Hawau Olamide Toyin, Humaid Alblooshi, Rufael Marew, Samar M. Magdy","submitted_at":"2025-05-26T20:15:15Z","abstract_excerpt":"We introduce ArVoice, a multi-speaker Modern Standard Arabic (MSA) speech corpus with diacritized transcriptions, intended for multi-speaker speech synthesis, and can be useful for other tasks such as speech-based diacritic restoration, voice conversion, and deepfake detection. ArVoice comprises: (1) a new professionally recorded set from six voice talents with diverse demographics, (2) a modified subset of the Arabic Speech Corpus; and (3) high-quality synthetic speech from two commercial systems. The complete corpus consists of a total of 83.52 hours of speech across 11 voices; around 10 hou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20506","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/2505.20506/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":"2505.20506","created_at":"2026-07-05T11:10:13.780042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20506v1","created_at":"2026-07-05T11:10:13.780042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20506","created_at":"2026-07-05T11:10:13.780042+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS36KDCYV7T5","created_at":"2026-07-05T11:10:13.780042+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS36KDCYV7T5JUDH","created_at":"2026-07-05T11:10:13.780042+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS36KDCY","created_at":"2026-07-05T11:10:13.780042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20506","citing_title":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF","json":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF.json","graph_json":"https://pith.science/api/pith-number/DS36KDCYV7T5JUDHESOIPU22YF/graph.json","events_json":"https://pith.science/api/pith-number/DS36KDCYV7T5JUDHESOIPU22YF/events.json","paper":"https://pith.science/paper/DS36KDCY"},"agent_actions":{"view_html":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF","download_json":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF.json","view_paper":"https://pith.science/paper/DS36KDCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20506&json=true","fetch_graph":"https://pith.science/api/pith-number/DS36KDCYV7T5JUDHESOIPU22YF/graph.json","fetch_events":"https://pith.science/api/pith-number/DS36KDCYV7T5JUDHESOIPU22YF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF/action/storage_attestation","attest_author":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF/action/author_attestation","sign_citation":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF/action/citation_signature","submit_replication":"https://pith.science/pith/DS36KDCYV7T5JUDHESOIPU22YF/action/replication_record"}},"created_at":"2026-07-05T11:10:13.780042+00:00","updated_at":"2026-07-05T11:10:13.780042+00:00"}