{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EDDJMVCI5TJMOVHUJF7KUXDETA","short_pith_number":"pith:EDDJMVCI","schema_version":"1.0","canonical_sha256":"20c6965448ecd2c754f4497eaa5c64980cbe95c2ebdb1cfeca210a3fc2d83d67","source":{"kind":"arxiv","id":"2104.08459","version":3},"attestation_state":"computed","paper":{"title":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aigerim Janaliyeva, Almas Mirzakhmetov, Huseyin Atakan Varol, Saida Mussakhojayeva, Yerbolat Khassanov","submitted_at":"2021-04-17T05:49:57Z","abstract_excerpt":"This paper introduces a high-quality open-source speech synthesis dataset for Kazakh, a low-resource language spoken by over 13 million people worldwide. The dataset consists of about 93 hours of transcribed audio recordings spoken by two professional speakers (female and male). It is the first publicly available large-scale dataset developed to promote Kazakh text-to-speech (TTS) applications in both academia and industry. In this paper, we share our experience by describing the dataset development procedures and faced challenges, and discuss important future directions. To demonstrate the re"},"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":"2104.08459","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-17T05:49:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"17b1547b0cdf9965447aaa7ae84338d329e4f303c3333f1abdc9db4b91ee20cb","abstract_canon_sha256":"3389f8d8838654114a72e18d6a23c26d4da06de52b05e9949d401e95a29399e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:38.526281Z","signature_b64":"wviRH29wh/ymaVzrI9iHw3wtz2nJ2nOBLsmxjjkyIgjAtjiR4VaM5ANUBqzx8Tz0fnUyrZlvZTkU67DI2INiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20c6965448ecd2c754f4497eaa5c64980cbe95c2ebdb1cfeca210a3fc2d83d67","last_reissued_at":"2026-07-05T03:12:38.525871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:38.525871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aigerim Janaliyeva, Almas Mirzakhmetov, Huseyin Atakan Varol, Saida Mussakhojayeva, Yerbolat Khassanov","submitted_at":"2021-04-17T05:49:57Z","abstract_excerpt":"This paper introduces a high-quality open-source speech synthesis dataset for Kazakh, a low-resource language spoken by over 13 million people worldwide. The dataset consists of about 93 hours of transcribed audio recordings spoken by two professional speakers (female and male). It is the first publicly available large-scale dataset developed to promote Kazakh text-to-speech (TTS) applications in both academia and industry. In this paper, we share our experience by describing the dataset development procedures and faced challenges, and discuss important future directions. To demonstrate the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08459","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/2104.08459/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":"2104.08459","created_at":"2026-07-05T03:12:38.525932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08459v3","created_at":"2026-07-05T03:12:38.525932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08459","created_at":"2026-07-05T03:12:38.525932+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDDJMVCI5TJM","created_at":"2026-07-05T03:12:38.525932+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDDJMVCI5TJMOVHU","created_at":"2026-07-05T03:12:38.525932+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDDJMVCI","created_at":"2026-07-05T03:12:38.525932+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/EDDJMVCI5TJMOVHUJF7KUXDETA","json":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA.json","graph_json":"https://pith.science/api/pith-number/EDDJMVCI5TJMOVHUJF7KUXDETA/graph.json","events_json":"https://pith.science/api/pith-number/EDDJMVCI5TJMOVHUJF7KUXDETA/events.json","paper":"https://pith.science/paper/EDDJMVCI"},"agent_actions":{"view_html":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA","download_json":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA.json","view_paper":"https://pith.science/paper/EDDJMVCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08459&json=true","fetch_graph":"https://pith.science/api/pith-number/EDDJMVCI5TJMOVHUJF7KUXDETA/graph.json","fetch_events":"https://pith.science/api/pith-number/EDDJMVCI5TJMOVHUJF7KUXDETA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA/action/storage_attestation","attest_author":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA/action/author_attestation","sign_citation":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA/action/citation_signature","submit_replication":"https://pith.science/pith/EDDJMVCI5TJMOVHUJF7KUXDETA/action/replication_record"}},"created_at":"2026-07-05T03:12:38.525932+00:00","updated_at":"2026-07-05T03:12:38.525932+00:00"}