{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BWJERMYEN4EUG3LX2UTOR5URTS","short_pith_number":"pith:BWJERMYE","schema_version":"1.0","canonical_sha256":"0d9248b3046f09436d77d526e8f6919ca22dd0ec960afe819f715cc8b7cc15ff","source":{"kind":"arxiv","id":"1906.09426","version":1},"attestation_state":"computed","paper":{"title":"End-to-End ASR for Code-switched Hindi-English Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Basil Abraham, Brij Mohan Lal Srivastava, Preethi Jyothi, Rupesh Mehta, Sunayana Sitaram","submitted_at":"2019-06-22T10:23:42Z","abstract_excerpt":"End-to-end (E2E) models have been explored for large speech corpora and have been found to match or outperform traditional pipeline-based systems in some languages. However, most prior work on end-to-end models use speech corpora exceeding hundreds or thousands of hours. In this study, we explore end-to-end models for code-switched Hindi-English language with less than 50 hours of data. We utilize two specific measures to improve network performance in the low-resource setting, namely multi-task learning (MTL) and balancing the corpus to deal with the inherent class imbalance problem i.e. the "},"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":"1906.09426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-22T10:23:42Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"cc328a7ebd233f252da3407aa12e3e9b69e0641a74e109146d21167f3157235f","abstract_canon_sha256":"882faf7f5874820a676b33ec7081280ddb3eb3724b17176c5070573eafb4088c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:38.120143Z","signature_b64":"yW6wpiiAb/d90oIVJdALiPJJUhoVqEXlnVNEs1sEJWhESpZDqytprKS5HNtSrC7yMXu/luX8kq33ClXqABxXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d9248b3046f09436d77d526e8f6919ca22dd0ec960afe819f715cc8b7cc15ff","last_reissued_at":"2026-05-17T23:42:38.119415Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:38.119415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End ASR for Code-switched Hindi-English Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Basil Abraham, Brij Mohan Lal Srivastava, Preethi Jyothi, Rupesh Mehta, Sunayana Sitaram","submitted_at":"2019-06-22T10:23:42Z","abstract_excerpt":"End-to-end (E2E) models have been explored for large speech corpora and have been found to match or outperform traditional pipeline-based systems in some languages. However, most prior work on end-to-end models use speech corpora exceeding hundreds or thousands of hours. In this study, we explore end-to-end models for code-switched Hindi-English language with less than 50 hours of data. We utilize two specific measures to improve network performance in the low-resource setting, namely multi-task learning (MTL) and balancing the corpus to deal with the inherent class imbalance problem i.e. the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09426","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":""},"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":"1906.09426","created_at":"2026-05-17T23:42:38.119516+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09426v1","created_at":"2026-05-17T23:42:38.119516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09426","created_at":"2026-05-17T23:42:38.119516+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWJERMYEN4EU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWJERMYEN4EUG3LX","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWJERMYE","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09426","citing_title":"End-to-End ASR for Code-switched Hindi-English Speech","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS","json":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS.json","graph_json":"https://pith.science/api/pith-number/BWJERMYEN4EUG3LX2UTOR5URTS/graph.json","events_json":"https://pith.science/api/pith-number/BWJERMYEN4EUG3LX2UTOR5URTS/events.json","paper":"https://pith.science/paper/BWJERMYE"},"agent_actions":{"view_html":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS","download_json":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS.json","view_paper":"https://pith.science/paper/BWJERMYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09426&json=true","fetch_graph":"https://pith.science/api/pith-number/BWJERMYEN4EUG3LX2UTOR5URTS/graph.json","fetch_events":"https://pith.science/api/pith-number/BWJERMYEN4EUG3LX2UTOR5URTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS/action/storage_attestation","attest_author":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS/action/author_attestation","sign_citation":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS/action/citation_signature","submit_replication":"https://pith.science/pith/BWJERMYEN4EUG3LX2UTOR5URTS/action/replication_record"}},"created_at":"2026-05-17T23:42:38.119516+00:00","updated_at":"2026-05-17T23:42:38.119516+00:00"}