{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QTSQWAA6YJTGBJCKSCIAO5ICO5","short_pith_number":"pith:QTSQWAA6","schema_version":"1.0","canonical_sha256":"84e50b001ec26660a44a9090077502777d8b16ad8fa903c87d64b7068151f166","source":{"kind":"arxiv","id":"2307.07295","version":1},"attestation_state":"computed","paper":{"title":"Towards dialect-inclusive recognition in a low-resource language: are balanced corpora the answer?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ailbhe N\\'i Chasaide, Christer Gobl, Liam Lonergan, Mengjie Qian, Neasa N\\'i Chiar\\'ain","submitted_at":"2023-07-14T12:18:38Z","abstract_excerpt":"ASR systems are generally built for the spoken 'standard', and their performance declines for non-standard dialects/varieties. This is a problem for a language like Irish, where there is no single spoken standard, but rather three major dialects: Ulster (Ul), Connacht (Co) and Munster (Mu). As a diagnostic to quantify the effect of the speaker's dialect on recognition performance, 12 ASR systems were trained, firstly using baseline dialect-balanced training corpora, and then using modified versions of the baseline corpora, where dialect-specific materials were either subtracted or added. Resul"},"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":"2307.07295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T12:18:38Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1737d519643df729a74081d618f8fc4d1698beef6d99e1856e9da28dd3e133a4","abstract_canon_sha256":"256f0ed43ecf72ba05769a8692dbc16167be84f23640477d3bc49a5c253a08e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:53.773412Z","signature_b64":"ld9U5PQE9elymHY/nftscjXj2Sc6IvxpqEZHtGB7rlOCbf5/+yoAiD78u6yX3dNRoP92XZuS5KCji+WqLTayAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84e50b001ec26660a44a9090077502777d8b16ad8fa903c87d64b7068151f166","last_reissued_at":"2026-07-05T06:30:53.773026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:53.773026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards dialect-inclusive recognition in a low-resource language: are balanced corpora the answer?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ailbhe N\\'i Chasaide, Christer Gobl, Liam Lonergan, Mengjie Qian, Neasa N\\'i Chiar\\'ain","submitted_at":"2023-07-14T12:18:38Z","abstract_excerpt":"ASR systems are generally built for the spoken 'standard', and their performance declines for non-standard dialects/varieties. This is a problem for a language like Irish, where there is no single spoken standard, but rather three major dialects: Ulster (Ul), Connacht (Co) and Munster (Mu). As a diagnostic to quantify the effect of the speaker's dialect on recognition performance, 12 ASR systems were trained, firstly using baseline dialect-balanced training corpora, and then using modified versions of the baseline corpora, where dialect-specific materials were either subtracted or added. Resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07295","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/2307.07295/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":"2307.07295","created_at":"2026-07-05T06:30:53.773088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07295v1","created_at":"2026-07-05T06:30:53.773088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07295","created_at":"2026-07-05T06:30:53.773088+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTSQWAA6YJTG","created_at":"2026-07-05T06:30:53.773088+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTSQWAA6YJTGBJCK","created_at":"2026-07-05T06:30:53.773088+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTSQWAA6","created_at":"2026-07-05T06:30:53.773088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10736","citing_title":"BlasBench: An Open Benchmark for Irish Speech Recognition","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5","json":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5.json","graph_json":"https://pith.science/api/pith-number/QTSQWAA6YJTGBJCKSCIAO5ICO5/graph.json","events_json":"https://pith.science/api/pith-number/QTSQWAA6YJTGBJCKSCIAO5ICO5/events.json","paper":"https://pith.science/paper/QTSQWAA6"},"agent_actions":{"view_html":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5","download_json":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5.json","view_paper":"https://pith.science/paper/QTSQWAA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07295&json=true","fetch_graph":"https://pith.science/api/pith-number/QTSQWAA6YJTGBJCKSCIAO5ICO5/graph.json","fetch_events":"https://pith.science/api/pith-number/QTSQWAA6YJTGBJCKSCIAO5ICO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5/action/storage_attestation","attest_author":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5/action/author_attestation","sign_citation":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5/action/citation_signature","submit_replication":"https://pith.science/pith/QTSQWAA6YJTGBJCKSCIAO5ICO5/action/replication_record"}},"created_at":"2026-07-05T06:30:53.773088+00:00","updated_at":"2026-07-05T06:30:53.773088+00:00"}