{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:COIAP5LHMESRPQIWJZYRMBT2AA","short_pith_number":"pith:COIAP5LH","schema_version":"1.0","canonical_sha256":"139007f567612517c1164e7116067a0000817cb2307f6d3bcf2d3b21e1336a35","source":{"kind":"arxiv","id":"2406.11727","version":2},"attestation_state":"computed","paper":{"title":"1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Abraham T. Owodunni, Babatunde Oladimeji, Eniola Alese, Kayode Olaleye, Naome A. Etori, Sewade Ogun, Tejumade Afonja, Tobi Olatunji, Tosin Adewumi","submitted_at":"2024-06-17T16:46:10Z","abstract_excerpt":"Recent advances in speech synthesis have enabled many useful applications like audio directions in Google Maps, screen readers, and automated content generation on platforms like TikTok. However, these systems are mostly dominated by voices sourced from data-rich geographies with personas representative of their source data. Although 3000 of the world's languages are domiciled in Africa, African voices and personas are under-represented in these systems. As speech synthesis becomes increasingly democratized, it is desirable to increase the representation of African English accents. We present "},"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":"2406.11727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T16:46:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"24b30f9dd8299cc64291b7f593d9e9b8aa2a1d7c2f741f27b516768adf19683b","abstract_canon_sha256":"4559c510dc6baf29a8546a279d650c4b298a85c77f96441b9058836842fa5804"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:20.653442Z","signature_b64":"hwPQLaYYJp00V7VX2+xWsAlf7dtzTrRfbYuNNiNNq+jO8O7ulUmoVRvceo0KtkicM6f42tK6wBR1WEtrGyYDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"139007f567612517c1164e7116067a0000817cb2307f6d3bcf2d3b21e1336a35","last_reissued_at":"2026-07-05T08:37:20.652946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:20.652946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Abraham T. Owodunni, Babatunde Oladimeji, Eniola Alese, Kayode Olaleye, Naome A. Etori, Sewade Ogun, Tejumade Afonja, Tobi Olatunji, Tosin Adewumi","submitted_at":"2024-06-17T16:46:10Z","abstract_excerpt":"Recent advances in speech synthesis have enabled many useful applications like audio directions in Google Maps, screen readers, and automated content generation on platforms like TikTok. However, these systems are mostly dominated by voices sourced from data-rich geographies with personas representative of their source data. Although 3000 of the world's languages are domiciled in Africa, African voices and personas are under-represented in these systems. As speech synthesis becomes increasingly democratized, it is desirable to increase the representation of African English accents. We present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11727","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/2406.11727/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":"2406.11727","created_at":"2026-07-05T08:37:20.653004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11727v2","created_at":"2026-07-05T08:37:20.653004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11727","created_at":"2026-07-05T08:37:20.653004+00:00"},{"alias_kind":"pith_short_12","alias_value":"COIAP5LHMESR","created_at":"2026-07-05T08:37:20.653004+00:00"},{"alias_kind":"pith_short_16","alias_value":"COIAP5LHMESRPQIW","created_at":"2026-07-05T08:37:20.653004+00:00"},{"alias_kind":"pith_short_8","alias_value":"COIAP5LH","created_at":"2026-07-05T08:37:20.653004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA","json":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA.json","graph_json":"https://pith.science/api/pith-number/COIAP5LHMESRPQIWJZYRMBT2AA/graph.json","events_json":"https://pith.science/api/pith-number/COIAP5LHMESRPQIWJZYRMBT2AA/events.json","paper":"https://pith.science/paper/COIAP5LH"},"agent_actions":{"view_html":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA","download_json":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA.json","view_paper":"https://pith.science/paper/COIAP5LH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11727&json=true","fetch_graph":"https://pith.science/api/pith-number/COIAP5LHMESRPQIWJZYRMBT2AA/graph.json","fetch_events":"https://pith.science/api/pith-number/COIAP5LHMESRPQIWJZYRMBT2AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA/action/storage_attestation","attest_author":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA/action/author_attestation","sign_citation":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA/action/citation_signature","submit_replication":"https://pith.science/pith/COIAP5LHMESRPQIWJZYRMBT2AA/action/replication_record"}},"created_at":"2026-07-05T08:37:20.653004+00:00","updated_at":"2026-07-05T08:37:20.653004+00:00"}