{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G4XZH3ZSHTGI6GVQ4LNA7EJG36","short_pith_number":"pith:G4XZH3ZS","schema_version":"1.0","canonical_sha256":"372f93ef323ccc8f1ab0e2da0f9126dfbb37fe89c25865e952758aa4489d7074","source":{"kind":"arxiv","id":"1907.03064","version":1},"attestation_state":"computed","paper":{"title":"Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Astik Biswas, Ewald van der Westhuizen, Raghav Menon, Thomas Niesler","submitted_at":"2019-07-06T02:53:10Z","abstract_excerpt":"We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support humanitarian relief programmes in rural Africa. Using just 1.57 hours of annotated speech data as a seed corpus, we increase the pool of training data by applying semi-supervised training to 17.55 hours of untranscribed speech. We make use of factorised time-delay neural networks (TDNN-F) for acoustic modelling, since these have recently been shown to be effect"},"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":"1907.03064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-06T02:53:10Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d31253b3a93b0d1129759d6b82ca549370a81a17252cbcb97b599546cb97adc3","abstract_canon_sha256":"c54ffaa5f1b6da95b62c378d7f0f2ed6af0a6f8aac1aeac69fbadedbd919171e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:19.013255Z","signature_b64":"N2UY9NM5EypJo8OUVxJHGUWf8J9UhzZQ/TDQQg0ULVhOtPcG1Dysd133TWNdsyiiEER4XHFpwhhKXSQZ9icCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"372f93ef323ccc8f1ab0e2da0f9126dfbb37fe89c25865e952758aa4489d7074","last_reissued_at":"2026-05-17T23:41:19.012827Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:19.012827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Astik Biswas, Ewald van der Westhuizen, Raghav Menon, Thomas Niesler","submitted_at":"2019-07-06T02:53:10Z","abstract_excerpt":"We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support humanitarian relief programmes in rural Africa. Using just 1.57 hours of annotated speech data as a seed corpus, we increase the pool of training data by applying semi-supervised training to 17.55 hours of untranscribed speech. We make use of factorised time-delay neural networks (TDNN-F) for acoustic modelling, since these have recently been shown to be effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03064","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":""},"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":"1907.03064","created_at":"2026-05-17T23:41:19.012897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03064v1","created_at":"2026-05-17T23:41:19.012897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03064","created_at":"2026-05-17T23:41:19.012897+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4XZH3ZSHTGI","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4XZH3ZSHTGI6GVQ","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4XZH3ZS","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03064","citing_title":"Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36","json":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36.json","graph_json":"https://pith.science/api/pith-number/G4XZH3ZSHTGI6GVQ4LNA7EJG36/graph.json","events_json":"https://pith.science/api/pith-number/G4XZH3ZSHTGI6GVQ4LNA7EJG36/events.json","paper":"https://pith.science/paper/G4XZH3ZS"},"agent_actions":{"view_html":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36","download_json":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36.json","view_paper":"https://pith.science/paper/G4XZH3ZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03064&json=true","fetch_graph":"https://pith.science/api/pith-number/G4XZH3ZSHTGI6GVQ4LNA7EJG36/graph.json","fetch_events":"https://pith.science/api/pith-number/G4XZH3ZSHTGI6GVQ4LNA7EJG36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36/action/storage_attestation","attest_author":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36/action/author_attestation","sign_citation":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36/action/citation_signature","submit_replication":"https://pith.science/pith/G4XZH3ZSHTGI6GVQ4LNA7EJG36/action/replication_record"}},"created_at":"2026-05-17T23:41:19.012897+00:00","updated_at":"2026-05-17T23:41:19.012897+00:00"}