{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2C35X2RWBSLVPYOZE6J4XUJS4I","short_pith_number":"pith:2C35X2RW","schema_version":"1.0","canonical_sha256":"d0b7dbea360c9757e1d92793cbd132e21a23d460b3196c36abf60835283a37d1","source":{"kind":"arxiv","id":"2111.10047","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abhinav Garg, Chanwoo Kim, Dhananjaya Gowda, Jiyeon Kim, Mehul Kumar","submitted_at":"2021-11-19T05:09:16Z","abstract_excerpt":"In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination of techniques such as transfer learning, encoder freezing, data augmentation using Text-To-Speech (TTS), and Semi-Supervised Learning (SSL). To improve the accuracy of a low-resource Italian ASR, we leverage a well-trained English model, unlabeled text corpus, and unlabeled audio corpus using transfer learning, TTS augmentation, and SSL respectively. In the first stage, we use transfer learning from a well-trained Eng"},"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":"2111.10047","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-11-19T05:09:16Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"de0f3c789c0eed9673d48a1390fbefb00ba528bf361c1bdc8224817d96d69b4f","abstract_canon_sha256":"c8a0574f5d1986d88e7960c1c0cdfba80dd6258aa1ee356e461ca91a02910f19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:27.182285Z","signature_b64":"iokXO+YmCcgiq52Vqk2eDT+JBfekswL0DeIgEBJcKzD+1wTBCpgoRmBk5Rd5+RdLjIKnTjDEnDt+lSxjPfH5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0b7dbea360c9757e1d92793cbd132e21a23d460b3196c36abf60835283a37d1","last_reissued_at":"2026-07-05T03:33:27.181793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:27.181793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abhinav Garg, Chanwoo Kim, Dhananjaya Gowda, Jiyeon Kim, Mehul Kumar","submitted_at":"2021-11-19T05:09:16Z","abstract_excerpt":"In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination of techniques such as transfer learning, encoder freezing, data augmentation using Text-To-Speech (TTS), and Semi-Supervised Learning (SSL). To improve the accuracy of a low-resource Italian ASR, we leverage a well-trained English model, unlabeled text corpus, and unlabeled audio corpus using transfer learning, TTS augmentation, and SSL respectively. In the first stage, we use transfer learning from a well-trained Eng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10047","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/2111.10047/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":"2111.10047","created_at":"2026-07-05T03:33:27.181856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10047v1","created_at":"2026-07-05T03:33:27.181856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10047","created_at":"2026-07-05T03:33:27.181856+00:00"},{"alias_kind":"pith_short_12","alias_value":"2C35X2RWBSLV","created_at":"2026-07-05T03:33:27.181856+00:00"},{"alias_kind":"pith_short_16","alias_value":"2C35X2RWBSLVPYOZ","created_at":"2026-07-05T03:33:27.181856+00:00"},{"alias_kind":"pith_short_8","alias_value":"2C35X2RW","created_at":"2026-07-05T03:33:27.181856+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/2C35X2RWBSLVPYOZE6J4XUJS4I","json":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I.json","graph_json":"https://pith.science/api/pith-number/2C35X2RWBSLVPYOZE6J4XUJS4I/graph.json","events_json":"https://pith.science/api/pith-number/2C35X2RWBSLVPYOZE6J4XUJS4I/events.json","paper":"https://pith.science/paper/2C35X2RW"},"agent_actions":{"view_html":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I","download_json":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I.json","view_paper":"https://pith.science/paper/2C35X2RW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10047&json=true","fetch_graph":"https://pith.science/api/pith-number/2C35X2RWBSLVPYOZE6J4XUJS4I/graph.json","fetch_events":"https://pith.science/api/pith-number/2C35X2RWBSLVPYOZE6J4XUJS4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I/action/storage_attestation","attest_author":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I/action/author_attestation","sign_citation":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I/action/citation_signature","submit_replication":"https://pith.science/pith/2C35X2RWBSLVPYOZE6J4XUJS4I/action/replication_record"}},"created_at":"2026-07-05T03:33:27.181856+00:00","updated_at":"2026-07-05T03:33:27.181856+00:00"}