{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZZGXWQIQ55XPRBE6GSVJ3KXVBN","short_pith_number":"pith:ZZGXWQIQ","schema_version":"1.0","canonical_sha256":"ce4d7b4110ef6ef8849e34aa9daaf50b639cbcfd4769d81dc28994a31a7e0d5d","source":{"kind":"arxiv","id":"2306.04428","version":2},"attestation_state":"computed","paper":{"title":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Bangiwe Zulu, Claytone Sikasote, David Zulu, Kalinda Siaminwe, Martin Phiri, Mayumbo Nyirenda, Mofya Phiri, Stanly Mwape","submitted_at":"2023-06-07T13:36:37Z","abstract_excerpt":"This work introduces Zambezi Voice, an open-source multilingual speech resource for Zambian languages. It contains two collections of datasets: unlabelled audio recordings of radio news and talk shows programs (160 hours) and labelled data (over 80 hours) consisting of read speech recorded from text sourced from publicly available literature books. The dataset is created for speech recognition but can be extended to multilingual speech processing research for both supervised and unsupervised learning approaches. To our knowledge, this is the first multilingual speech dataset created for Zambia"},"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":"2306.04428","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T13:36:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3fc9f815631fae0a9b4d93dc482b05314945a581f5193e5709a5f46feba6b7d0","abstract_canon_sha256":"2f9ae8f433fe3fdf05304c7bc38265d9b894e581b01cbc0a1072fc67b7b1011d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:44.888665Z","signature_b64":"h3zxGHH41si1pJZzvFp/HfMmOIHXqFjHRd3nvJhis4Ups6suizBBUydF/qgWQS4xyaRrKoulUtqStzcuOYPZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce4d7b4110ef6ef8849e34aa9daaf50b639cbcfd4769d81dc28994a31a7e0d5d","last_reissued_at":"2026-07-05T06:20:44.888306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:44.888306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Bangiwe Zulu, Claytone Sikasote, David Zulu, Kalinda Siaminwe, Martin Phiri, Mayumbo Nyirenda, Mofya Phiri, Stanly Mwape","submitted_at":"2023-06-07T13:36:37Z","abstract_excerpt":"This work introduces Zambezi Voice, an open-source multilingual speech resource for Zambian languages. It contains two collections of datasets: unlabelled audio recordings of radio news and talk shows programs (160 hours) and labelled data (over 80 hours) consisting of read speech recorded from text sourced from publicly available literature books. The dataset is created for speech recognition but can be extended to multilingual speech processing research for both supervised and unsupervised learning approaches. To our knowledge, this is the first multilingual speech dataset created for Zambia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04428","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/2306.04428/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":"2306.04428","created_at":"2026-07-05T06:20:44.888370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04428v2","created_at":"2026-07-05T06:20:44.888370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04428","created_at":"2026-07-05T06:20:44.888370+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZGXWQIQ55XP","created_at":"2026-07-05T06:20:44.888370+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZGXWQIQ55XPRBE6","created_at":"2026-07-05T06:20:44.888370+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZGXWQIQ","created_at":"2026-07-05T06:20:44.888370+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/ZZGXWQIQ55XPRBE6GSVJ3KXVBN","json":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN.json","graph_json":"https://pith.science/api/pith-number/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/graph.json","events_json":"https://pith.science/api/pith-number/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/events.json","paper":"https://pith.science/paper/ZZGXWQIQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN","download_json":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN.json","view_paper":"https://pith.science/paper/ZZGXWQIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04428&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/action/storage_attestation","attest_author":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/action/author_attestation","sign_citation":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/action/citation_signature","submit_replication":"https://pith.science/pith/ZZGXWQIQ55XPRBE6GSVJ3KXVBN/action/replication_record"}},"created_at":"2026-07-05T06:20:44.888370+00:00","updated_at":"2026-07-05T06:20:44.888370+00:00"}