{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZJUTJGQTYYFZNNR3BLOOKL74ZE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8"},"schema_version":"1.0","source":{"id":"2102.04889","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04889","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04889v1","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04889","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZJUTJGQTYYFZ","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZJUTJGQTYYFZNNR3","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZJUTJGQT","created_at":"2026-07-05T02:14:05Z"}],"graph_snapshots":[{"event_id":"sha256:afc412356bbd4f650cebdb2ec6e71fcf6ef558d7043222248459bbdac043c5a9","target":"graph","created_at":"2026-07-05T02:14:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.04889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Antonios Anastasopoulos, Claytone Sikasote","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04889","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:502be78b7b08eb5755366dcd5024a1dad5a26a736fdb6ecfc807df22d12bafc3","target":"record","created_at":"2026-07-05T02:14:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8"},"schema_version":"1.0","source":{"id":"2102.04889","kind":"arxiv","version":1}},"canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","first_computed_at":"2026-07-05T02:14:05.935576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:05.935576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2frtNH54z2vGJAT1fgIfP8QC1VJfrdh9ezkAEyzOXh9EIfC4qr7t94NUcb9xr2EkjHEJEEVxzuIg+lL1aYvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:05.936001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.04889","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:502be78b7b08eb5755366dcd5024a1dad5a26a736fdb6ecfc807df22d12bafc3","sha256:afc412356bbd4f650cebdb2ec6e71fcf6ef558d7043222248459bbdac043c5a9"],"state_sha256":"f238015d44504ed953a659c1aa011e038a2bc906254fb13fd6caad75506b352c"}