{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZJUTJGQTYYFZNNR3BLOOKL74ZE","short_pith_number":"pith:ZJUTJGQT","schema_version":"1.0","canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","source":{"kind":"arxiv","id":"2102.04889","version":1},"attestation_state":"computed","paper":{"title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Claytone Sikasote","submitted_at":"2021-02-09T15:42:00Z","abstract_excerpt":"We present a preprocessed, ready-to-use automatic speech recognition corpus, BembaSpeech, consisting over 24 hours of read speech in the Bemba language, a written but low-resourced language spoken by over 30% of the population in Zambia. To assess its usefulness for training and testing ASR systems for Bemba, we train an end-to-end Bemba ASR system by fine-tuning a pre-trained DeepSpeech English model on the training portion of the BembaSpeech corpus. Our best model achieves a word error rate (WER) of 54.78%. The results show that the corpus can be used for building ASR systems for Bemba. The "},"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":"2102.04889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","cross_cats_sorted":[],"title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8","abstract_canon_sha256":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:05.936001Z","signature_b64":"L2frtNH54z2vGJAT1fgIfP8QC1VJfrdh9ezkAEyzOXh9EIfC4qr7t94NUcb9xr2EkjHEJEEVxzuIg+lL1aYvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","last_reissued_at":"2026-07-05T02:14:05.935576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:05.935576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Claytone Sikasote","submitted_at":"2021-02-09T15:42:00Z","abstract_excerpt":"We present a preprocessed, ready-to-use automatic speech recognition corpus, BembaSpeech, consisting over 24 hours of read speech in the Bemba language, a written but low-resourced language spoken by over 30% of the population in Zambia. To assess its usefulness for training and testing ASR systems for Bemba, we train an end-to-end Bemba ASR system by fine-tuning a pre-trained DeepSpeech English model on the training portion of the BembaSpeech corpus. Our best model achieves a word error rate (WER) of 54.78%. The results show that the corpus can be used for building ASR systems for Bemba. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04889","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/2102.04889/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":"2102.04889","created_at":"2026-07-05T02:14:05.935635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04889v1","created_at":"2026-07-05T02:14:05.935635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04889","created_at":"2026-07-05T02:14:05.935635+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJUTJGQTYYFZ","created_at":"2026-07-05T02:14:05.935635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJUTJGQTYYFZNNR3","created_at":"2026-07-05T02:14:05.935635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJUTJGQT","created_at":"2026-07-05T02:14:05.935635+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/ZJUTJGQTYYFZNNR3BLOOKL74ZE","json":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE.json","graph_json":"https://pith.science/api/pith-number/ZJUTJGQTYYFZNNR3BLOOKL74ZE/graph.json","events_json":"https://pith.science/api/pith-number/ZJUTJGQTYYFZNNR3BLOOKL74ZE/events.json","paper":"https://pith.science/paper/ZJUTJGQT"},"agent_actions":{"view_html":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE","download_json":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE.json","view_paper":"https://pith.science/paper/ZJUTJGQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04889&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJUTJGQTYYFZNNR3BLOOKL74ZE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJUTJGQTYYFZNNR3BLOOKL74ZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/action/storage_attestation","attest_author":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/action/author_attestation","sign_citation":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/action/citation_signature","submit_replication":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/action/replication_record"}},"created_at":"2026-07-05T02:14:05.935635+00:00","updated_at":"2026-07-05T02:14:05.935635+00:00"}