{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ","short_pith_number":"pith:QEZEF4QE","schema_version":"1.0","canonical_sha256":"813242f204d5905fcb3f013d99953fc2610c718db1abdb867e108a51516c6d1c","source":{"kind":"arxiv","id":"2208.12666","version":1},"attestation_state":"computed","paper":{"title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Anoop Kunchukuttan, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sumanth Doddapaneni, Tahir Javed","submitted_at":"2022-08-26T13:37:45Z","abstract_excerpt":"End-to-end (E2E) models have become the default choice for state-of-the-art speech recognition systems. Such models are trained on large amounts of labelled data, which are often not available for low-resource languages. Techniques such as self-supervised learning and transfer learning hold promise, but have not yet been effective in training accurate models. On the other hand, collecting labelled datasets on a diverse set of domains and speakers is very expensive. In this work, we demonstrate an inexpensive and effective alternative to these approaches by ``mining'' text and audio pairs for I"},"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":"2208.12666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T13:37:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9b58758d382a1c1b7ce327406a772605fbc40f5b56ab3099c8524eabdae2d162","abstract_canon_sha256":"06df57536c0fb4885d1b43917162ef4dff842fe5c14b38462d06f52a01fdc59b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:48.482380Z","signature_b64":"PqfjJQIgHmbi+z8xcGOAMpXLijWTMOo4kC6Bg75fSEjz2O4+7q8/dP8svUSVZ9dAwl6iOHKNVz+5DLQ7tmtzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813242f204d5905fcb3f013d99953fc2610c718db1abdb867e108a51516c6d1c","last_reissued_at":"2026-07-05T04:51:48.481897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:48.481897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Anoop Kunchukuttan, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sumanth Doddapaneni, Tahir Javed","submitted_at":"2022-08-26T13:37:45Z","abstract_excerpt":"End-to-end (E2E) models have become the default choice for state-of-the-art speech recognition systems. Such models are trained on large amounts of labelled data, which are often not available for low-resource languages. Techniques such as self-supervised learning and transfer learning hold promise, but have not yet been effective in training accurate models. On the other hand, collecting labelled datasets on a diverse set of domains and speakers is very expensive. In this work, we demonstrate an inexpensive and effective alternative to these approaches by ``mining'' text and audio pairs for I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12666","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/2208.12666/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":"2208.12666","created_at":"2026-07-05T04:51:48.481955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.12666v1","created_at":"2026-07-05T04:51:48.481955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12666","created_at":"2026-07-05T04:51:48.481955+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEZEF4QE2WIF","created_at":"2026-07-05T04:51:48.481955+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEZEF4QE2WIF7SZ7","created_at":"2026-07-05T04:51:48.481955+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEZEF4QE","created_at":"2026-07-05T04:51:48.481955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14177","citing_title":"Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ","json":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ.json","graph_json":"https://pith.science/api/pith-number/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/graph.json","events_json":"https://pith.science/api/pith-number/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/events.json","paper":"https://pith.science/paper/QEZEF4QE"},"agent_actions":{"view_html":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ","download_json":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ.json","view_paper":"https://pith.science/paper/QEZEF4QE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.12666&json=true","fetch_graph":"https://pith.science/api/pith-number/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/action/storage_attestation","attest_author":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/action/author_attestation","sign_citation":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/action/citation_signature","submit_replication":"https://pith.science/pith/QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ/action/replication_record"}},"created_at":"2026-07-05T04:51:48.481955+00:00","updated_at":"2026-07-05T04:51:48.481955+00:00"}