{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6PHBBIKK4JX3Y7ROFOMQV7ECVK","short_pith_number":"pith:6PHBBIKK","schema_version":"1.0","canonical_sha256":"f3ce10a14ae26fbc7e2e2b990afc82aa9768209dc2d55e312e0631701e6684db","source":{"kind":"arxiv","id":"2305.10951","version":2},"attestation_state":"computed","paper":{"title":"Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bradley McDonnell, Dan Jurafsky, Martijn Bartelds, Martijn Wieling, Nay San","submitted_at":"2023-05-18T13:20:38Z","abstract_excerpt":"The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages, such as minority languages, regional languages or dialects, ASR performance generally remains much lower. In this study, we investigate whether data augmentation techniques could help improve low-resource ASR performance, focusing on four typologically diverse minority languages or language variants (West Germanic: Gronings, West-Frisian; Malayo-Polynesian: Bes"},"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":"2305.10951","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T13:20:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d9a9c6d02c05f79c6e1a939676440d802d418ea1b36def4da213c3c83d650f70","abstract_canon_sha256":"5bd5246d54d584fbd5c4c4dd5af6a03c140e71057002ec6e4c6547dab98584bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:33.455895Z","signature_b64":"heq5JjpIBp2zeKKWQqlZKRZWzKImIWPccht2Ac+g+3i+MEcQSlzp5b5nDGnyiXeNew9+KX/B9pPEbJomIYARCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3ce10a14ae26fbc7e2e2b990afc82aa9768209dc2d55e312e0631701e6684db","last_reissued_at":"2026-07-05T06:11:33.455427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:33.455427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bradley McDonnell, Dan Jurafsky, Martijn Bartelds, Martijn Wieling, Nay San","submitted_at":"2023-05-18T13:20:38Z","abstract_excerpt":"The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages, such as minority languages, regional languages or dialects, ASR performance generally remains much lower. In this study, we investigate whether data augmentation techniques could help improve low-resource ASR performance, focusing on four typologically diverse minority languages or language variants (West Germanic: Gronings, West-Frisian; Malayo-Polynesian: Bes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10951","kind":"arxiv","version":2},"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/2305.10951/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":"2305.10951","created_at":"2026-07-05T06:11:33.455489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10951v2","created_at":"2026-07-05T06:11:33.455489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10951","created_at":"2026-07-05T06:11:33.455489+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PHBBIKK4JX3","created_at":"2026-07-05T06:11:33.455489+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PHBBIKK4JX3Y7RO","created_at":"2026-07-05T06:11:33.455489+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PHBBIKK","created_at":"2026-07-05T06:11:33.455489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22810","citing_title":"A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK","json":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK.json","graph_json":"https://pith.science/api/pith-number/6PHBBIKK4JX3Y7ROFOMQV7ECVK/graph.json","events_json":"https://pith.science/api/pith-number/6PHBBIKK4JX3Y7ROFOMQV7ECVK/events.json","paper":"https://pith.science/paper/6PHBBIKK"},"agent_actions":{"view_html":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK","download_json":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK.json","view_paper":"https://pith.science/paper/6PHBBIKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10951&json=true","fetch_graph":"https://pith.science/api/pith-number/6PHBBIKK4JX3Y7ROFOMQV7ECVK/graph.json","fetch_events":"https://pith.science/api/pith-number/6PHBBIKK4JX3Y7ROFOMQV7ECVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK/action/storage_attestation","attest_author":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK/action/author_attestation","sign_citation":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK/action/citation_signature","submit_replication":"https://pith.science/pith/6PHBBIKK4JX3Y7ROFOMQV7ECVK/action/replication_record"}},"created_at":"2026-07-05T06:11:33.455489+00:00","updated_at":"2026-07-05T06:11:33.455489+00:00"}