{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XYE6W4PCH354W3IIDTPJDVSZT6","short_pith_number":"pith:XYE6W4PC","schema_version":"1.0","canonical_sha256":"be09eb71e23efbcb6d081cde91d6599faa77e11adf51cad80d062b7fbf348d1d","source":{"kind":"arxiv","id":"2406.02561","version":3},"attestation_state":"computed","paper":{"title":"Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abdulhady Abas Abdullah, Hadi Veisi, Tarik Rashid","submitted_at":"2024-04-23T10:47:56Z","abstract_excerpt":"End-to-end transformer-based models epitomize the cutting-edge in Automatic Speech Recognition (ASR) systems. Despite their substantial benefits, these models demand extensive training data to perform optimally, presenting a significant challenge for low-resource languages such as Central Kurdish. Addressing this issue requires innovative methods and techniques. This paper aims to develop an ASR system for Intermediate Kurdish by collecting a robust corpus of speech, using the N-GRAM language model, and utilizing an external Kurdish tokenizer for refinement and integration techniques to enhanc"},"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":"2406.02561","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-23T10:47:56Z","cross_cats_sorted":[],"title_canon_sha256":"08066a6762976fc338595d3123e1d0d07f59accc780d29b82d4a7774131f4a49","abstract_canon_sha256":"9e289f1bbb0171095cc881a5c4a92ad3de1a2e639238ecbe0729b6708e98d361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:36.814202Z","signature_b64":"lF7Onxjaa35v/sJ3SB0QVSTkraSKImayDwbIumkZ2d3vw0luh2ooXXi7qd9I1oq0zDSA+dQ87OGlPYgoiMGQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be09eb71e23efbcb6d081cde91d6599faa77e11adf51cad80d062b7fbf348d1d","last_reissued_at":"2026-07-05T09:04:36.813756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:36.813756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abdulhady Abas Abdullah, Hadi Veisi, Tarik Rashid","submitted_at":"2024-04-23T10:47:56Z","abstract_excerpt":"End-to-end transformer-based models epitomize the cutting-edge in Automatic Speech Recognition (ASR) systems. Despite their substantial benefits, these models demand extensive training data to perform optimally, presenting a significant challenge for low-resource languages such as Central Kurdish. Addressing this issue requires innovative methods and techniques. This paper aims to develop an ASR system for Intermediate Kurdish by collecting a robust corpus of speech, using the N-GRAM language model, and utilizing an external Kurdish tokenizer for refinement and integration techniques to enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02561","kind":"arxiv","version":3},"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/2406.02561/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":"2406.02561","created_at":"2026-07-05T09:04:36.813830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02561v3","created_at":"2026-07-05T09:04:36.813830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02561","created_at":"2026-07-05T09:04:36.813830+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYE6W4PCH354","created_at":"2026-07-05T09:04:36.813830+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYE6W4PCH354W3II","created_at":"2026-07-05T09:04:36.813830+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYE6W4PC","created_at":"2026-07-05T09:04:36.813830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18582","citing_title":"Speaker Diarization for Low-Resource Languages Through Wav2vec Fine-Tuning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6","json":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6.json","graph_json":"https://pith.science/api/pith-number/XYE6W4PCH354W3IIDTPJDVSZT6/graph.json","events_json":"https://pith.science/api/pith-number/XYE6W4PCH354W3IIDTPJDVSZT6/events.json","paper":"https://pith.science/paper/XYE6W4PC"},"agent_actions":{"view_html":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6","download_json":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6.json","view_paper":"https://pith.science/paper/XYE6W4PC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02561&json=true","fetch_graph":"https://pith.science/api/pith-number/XYE6W4PCH354W3IIDTPJDVSZT6/graph.json","fetch_events":"https://pith.science/api/pith-number/XYE6W4PCH354W3IIDTPJDVSZT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6/action/storage_attestation","attest_author":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6/action/author_attestation","sign_citation":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6/action/citation_signature","submit_replication":"https://pith.science/pith/XYE6W4PCH354W3IIDTPJDVSZT6/action/replication_record"}},"created_at":"2026-07-05T09:04:36.813830+00:00","updated_at":"2026-07-05T09:04:36.813830+00:00"}