{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XQQ63AR67Z5EXHPG2UJX4NFLJD","short_pith_number":"pith:XQQ63AR6","schema_version":"1.0","canonical_sha256":"bc21ed823efe7a4b9de6d5137e34ab48e110f4e511a2a18469c47df2bd17278c","source":{"kind":"arxiv","id":"2307.16071","version":2},"attestation_state":"computed","paper":{"title":"\\`{I}r\\`{o}y\\`{i}nSpeech: A multi-purpose Yor\\`{u}b\\'{a} Speech Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anuoluwapo Aremu, David Ifeoluwa Adelani, Iroro Orife, Kola Tubosun, Tolulope Ogunremi","submitted_at":"2023-07-29T20:42:50Z","abstract_excerpt":"We introduce \\`{I}r\\`{o}y\\`{i}nSpeech, a new corpus influenced by the desire to increase the amount of high quality, contemporary Yor\\`{u}b\\'{a} speech data, which can be used for both Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) tasks. We curated about 23000 text sentences from news and creative writing domains with the open license CC-BY-4.0. To encourage a participatory approach to data creation, we provide 5000 curated sentences to the Mozilla Common Voice platform to crowd-source the recording and validation of Yor\\`{u}b\\'{a} speech data. In total, we created about 42 hours"},"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":"2307.16071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-29T20:42:50Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"931d1618f84e832966fb42bf448bdbd65c29ac05a65a53d2f730326e42267634","abstract_canon_sha256":"2238e79cd0b4b2b322b76a4f29ceeaa9979cba4cecca2ca2a88d084f529befa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:14.962253Z","signature_b64":"PE5pe1EsnrmLhGVlJMLFIGSF2my1xfqlUDTXj3IE29Jb4RqgiFYTEMB/ZbEiKrbNa6q9Cxy6nT/vv+zotnH2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc21ed823efe7a4b9de6d5137e34ab48e110f4e511a2a18469c47df2bd17278c","last_reissued_at":"2026-07-05T08:01:14.961785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:14.961785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\\`{I}r\\`{o}y\\`{i}nSpeech: A multi-purpose Yor\\`{u}b\\'{a} Speech Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anuoluwapo Aremu, David Ifeoluwa Adelani, Iroro Orife, Kola Tubosun, Tolulope Ogunremi","submitted_at":"2023-07-29T20:42:50Z","abstract_excerpt":"We introduce \\`{I}r\\`{o}y\\`{i}nSpeech, a new corpus influenced by the desire to increase the amount of high quality, contemporary Yor\\`{u}b\\'{a} speech data, which can be used for both Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) tasks. We curated about 23000 text sentences from news and creative writing domains with the open license CC-BY-4.0. To encourage a participatory approach to data creation, we provide 5000 curated sentences to the Mozilla Common Voice platform to crowd-source the recording and validation of Yor\\`{u}b\\'{a} speech data. In total, we created about 42 hours"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16071","kind":"arxiv","version":2},"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/2307.16071/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":"2307.16071","created_at":"2026-07-05T08:01:14.961841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16071v2","created_at":"2026-07-05T08:01:14.961841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16071","created_at":"2026-07-05T08:01:14.961841+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQQ63AR67Z5E","created_at":"2026-07-05T08:01:14.961841+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQQ63AR67Z5EXHPG","created_at":"2026-07-05T08:01:14.961841+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQQ63AR6","created_at":"2026-07-05T08:01:14.961841+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/XQQ63AR67Z5EXHPG2UJX4NFLJD","json":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD.json","graph_json":"https://pith.science/api/pith-number/XQQ63AR67Z5EXHPG2UJX4NFLJD/graph.json","events_json":"https://pith.science/api/pith-number/XQQ63AR67Z5EXHPG2UJX4NFLJD/events.json","paper":"https://pith.science/paper/XQQ63AR6"},"agent_actions":{"view_html":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD","download_json":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD.json","view_paper":"https://pith.science/paper/XQQ63AR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16071&json=true","fetch_graph":"https://pith.science/api/pith-number/XQQ63AR67Z5EXHPG2UJX4NFLJD/graph.json","fetch_events":"https://pith.science/api/pith-number/XQQ63AR67Z5EXHPG2UJX4NFLJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD/action/storage_attestation","attest_author":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD/action/author_attestation","sign_citation":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD/action/citation_signature","submit_replication":"https://pith.science/pith/XQQ63AR67Z5EXHPG2UJX4NFLJD/action/replication_record"}},"created_at":"2026-07-05T08:01:14.961841+00:00","updated_at":"2026-07-05T08:01:14.961841+00:00"}