{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7Q4LM7ZESY6HA35I7AMX3PEMPC","short_pith_number":"pith:7Q4LM7ZE","schema_version":"1.0","canonical_sha256":"fc38b67f24963c706fa8f8197dbc8c788114f74998e895d99a02eb4d2614a089","source":{"kind":"arxiv","id":"2501.14788","version":2},"attestation_state":"computed","paper":{"title":"Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexan Ayrapetyan, Ara Yeroyan, Boris Ginsburg, Mher Yerznkanyan, Nikolay Karpov, Nune Tadevosyan, Sofia Kostandian, Vitaly Lavrukhin","submitted_at":"2025-01-08T15:18:42Z","abstract_excerpt":"This study explores methods to increase data volume for low-resource languages using techniques such as crowdsourcing, pseudo-labeling, advanced data preprocessing and various permissive data sources such as audiobooks, Common Voice, YouTube. While these methods are well-explored for highresource languages, their application for low-resource languages remains underexplored. Using Armenian and Georgian as case studies, we demonstrate how linguistic and resource-specific characteristics influence the success of these methods. This work provides practical guidance for researchers to choose cost-e"},"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":"2501.14788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-08T15:18:42Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"8b82ee82c4425b9bc06ef8a4f614a0cd9f7a232ab244cdd7989ab480eff5e6d1","abstract_canon_sha256":"bf06b1e9048a2f5fcfa94718405ac90b09e070630506a9697d3031f76338d374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:48.283744Z","signature_b64":"Q7uxDihZ5gAU8bGFwTdQzN4aYwii7MR4VaNLdK30s6JhBqDNSHmjcRFtKDNmV5ynmv8/tminrBkiGWlDAiVdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc38b67f24963c706fa8f8197dbc8c788114f74998e895d99a02eb4d2614a089","last_reissued_at":"2026-07-05T10:10:48.283265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:48.283265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexan Ayrapetyan, Ara Yeroyan, Boris Ginsburg, Mher Yerznkanyan, Nikolay Karpov, Nune Tadevosyan, Sofia Kostandian, Vitaly Lavrukhin","submitted_at":"2025-01-08T15:18:42Z","abstract_excerpt":"This study explores methods to increase data volume for low-resource languages using techniques such as crowdsourcing, pseudo-labeling, advanced data preprocessing and various permissive data sources such as audiobooks, Common Voice, YouTube. While these methods are well-explored for highresource languages, their application for low-resource languages remains underexplored. Using Armenian and Georgian as case studies, we demonstrate how linguistic and resource-specific characteristics influence the success of these methods. This work provides practical guidance for researchers to choose cost-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14788","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/2501.14788/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":"2501.14788","created_at":"2026-07-05T10:10:48.283323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14788v2","created_at":"2026-07-05T10:10:48.283323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14788","created_at":"2026-07-05T10:10:48.283323+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q4LM7ZESY6H","created_at":"2026-07-05T10:10:48.283323+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q4LM7ZESY6HA35I","created_at":"2026-07-05T10:10:48.283323+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q4LM7ZE","created_at":"2026-07-05T10:10:48.283323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC","json":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC.json","graph_json":"https://pith.science/api/pith-number/7Q4LM7ZESY6HA35I7AMX3PEMPC/graph.json","events_json":"https://pith.science/api/pith-number/7Q4LM7ZESY6HA35I7AMX3PEMPC/events.json","paper":"https://pith.science/paper/7Q4LM7ZE"},"agent_actions":{"view_html":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC","download_json":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC.json","view_paper":"https://pith.science/paper/7Q4LM7ZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14788&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q4LM7ZESY6HA35I7AMX3PEMPC/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q4LM7ZESY6HA35I7AMX3PEMPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC/action/storage_attestation","attest_author":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC/action/author_attestation","sign_citation":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC/action/citation_signature","submit_replication":"https://pith.science/pith/7Q4LM7ZESY6HA35I7AMX3PEMPC/action/replication_record"}},"created_at":"2026-07-05T10:10:48.283323+00:00","updated_at":"2026-07-05T10:10:48.283323+00:00"}