{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P4MSDKC2FWUXXY2QZLRLOCCBJ2","short_pith_number":"pith:P4MSDKC2","schema_version":"1.0","canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","source":{"kind":"arxiv","id":"1811.00241","version":2},"attestation_state":"computed","paper":{"title":"On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eng Siong Chng, Haihua Xu, Haizhou Li, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2018-11-01T05:29:02Z","abstract_excerpt":"Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end (E2E) approaches to the Mandarin-English code-switching speech recognition (CSSR) task. We first examine the effectiveness of using data augmentation and byte-pair encoding (BPE) subword units. More importantly, we propose a multitask learning recipe, where a language identification task is explicitly learned in addition to the E2E speech recognition task. Furthermore, we introduce an efficient word vocabulary expans"},"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":"1811.00241","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T05:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"000dd962815340dd97aeae4ce7811882011d39e25fb2c4ce16c85490ad357dda","abstract_canon_sha256":"a378c1ca4f8d974ee557dd0250d2a29b80d352e6614a05f9d49b12081832d68d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:55.759273Z","signature_b64":"YQ+xLMUI5q+kaIIBGb0oEZZkdssyotVCNmgUGAovI/zu7X1r+tHbszihAyDbmEKgUzg+c3Q6EBrru1mjBtplBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","last_reissued_at":"2026-05-17T23:40:55.758665Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:55.758665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eng Siong Chng, Haihua Xu, Haizhou Li, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2018-11-01T05:29:02Z","abstract_excerpt":"Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end (E2E) approaches to the Mandarin-English code-switching speech recognition (CSSR) task. We first examine the effectiveness of using data augmentation and byte-pair encoding (BPE) subword units. More importantly, we propose a multitask learning recipe, where a language identification task is explicitly learned in addition to the E2E speech recognition task. Furthermore, we introduce an efficient word vocabulary expans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00241","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":""},"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":"1811.00241","created_at":"2026-05-17T23:40:55.758775+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00241v2","created_at":"2026-05-17T23:40:55.758775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00241","created_at":"2026-05-17T23:40:55.758775+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4MSDKC2FWUX","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4MSDKC2FWUXXY2Q","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4MSDKC2","created_at":"2026-05-18T12:32:43.782077+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/P4MSDKC2FWUXXY2QZLRLOCCBJ2","json":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2.json","graph_json":"https://pith.science/api/pith-number/P4MSDKC2FWUXXY2QZLRLOCCBJ2/graph.json","events_json":"https://pith.science/api/pith-number/P4MSDKC2FWUXXY2QZLRLOCCBJ2/events.json","paper":"https://pith.science/paper/P4MSDKC2"},"agent_actions":{"view_html":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2","download_json":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2.json","view_paper":"https://pith.science/paper/P4MSDKC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00241&json=true","fetch_graph":"https://pith.science/api/pith-number/P4MSDKC2FWUXXY2QZLRLOCCBJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/P4MSDKC2FWUXXY2QZLRLOCCBJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/action/storage_attestation","attest_author":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/action/author_attestation","sign_citation":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/action/citation_signature","submit_replication":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/action/replication_record"}},"created_at":"2026-05-17T23:40:55.758775+00:00","updated_at":"2026-05-17T23:40:55.758775+00:00"}