{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZXOMOHE37A6LS4ZXLA3FEDNW3E","short_pith_number":"pith:ZXOMOHE3","schema_version":"1.0","canonical_sha256":"cddcc71c9bf83cb973375836520db6d937b402c379c16820de4fa642379ea934","source":{"kind":"arxiv","id":"1904.03802","version":2},"attestation_state":"computed","paper":{"title":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ma, Chongjia Ni, Eng Siong Chng, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2019-04-08T02:16:44Z","abstract_excerpt":"The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end code-switching ASR using only monolingual data. Our method encourages the distributions of output token embeddings of monolingual languages to be similar, and hence, promotes the ASR model to easily code-switch between languages. Specifically, we propose to use Jensen-Shannon divergence and cosine distance based constraints. The former will enforce output embeddings of mono"},"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":"1904.03802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T02:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"a8975cb6e85d19d00230500c29c34cb0a5ee0fa7a8eafdd2a2d8aa640217702b","abstract_canon_sha256":"cfad10b50ac12a98c9040587f1cbc3ed6858ada2ec845dd0ddb5ddc83d4ff70b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:28.612804Z","signature_b64":"XPDjMRPnnaKt4h93ex426hGKkpF1RzoTWHOOYfxPJcuROyP5i3wJyXFD4xk0T6XpcAlLJ6jXMVOmteHWhuXtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cddcc71c9bf83cb973375836520db6d937b402c379c16820de4fa642379ea934","last_reissued_at":"2026-07-05T02:06:28.612394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:28.612394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ma, Chongjia Ni, Eng Siong Chng, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2019-04-08T02:16:44Z","abstract_excerpt":"The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end code-switching ASR using only monolingual data. Our method encourages the distributions of output token embeddings of monolingual languages to be similar, and hence, promotes the ASR model to easily code-switch between languages. Specifically, we propose to use Jensen-Shannon divergence and cosine distance based constraints. The former will enforce output embeddings of mono"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03802","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/1904.03802/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":"1904.03802","created_at":"2026-07-05T02:06:28.612453+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03802v2","created_at":"2026-07-05T02:06:28.612453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03802","created_at":"2026-07-05T02:06:28.612453+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXOMOHE37A6L","created_at":"2026-07-05T02:06:28.612453+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXOMOHE37A6LS4ZX","created_at":"2026-07-05T02:06:28.612453+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXOMOHE3","created_at":"2026-07-05T02:06:28.612453+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/ZXOMOHE37A6LS4ZXLA3FEDNW3E","json":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E.json","graph_json":"https://pith.science/api/pith-number/ZXOMOHE37A6LS4ZXLA3FEDNW3E/graph.json","events_json":"https://pith.science/api/pith-number/ZXOMOHE37A6LS4ZXLA3FEDNW3E/events.json","paper":"https://pith.science/paper/ZXOMOHE3"},"agent_actions":{"view_html":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E","download_json":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E.json","view_paper":"https://pith.science/paper/ZXOMOHE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03802&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXOMOHE37A6LS4ZXLA3FEDNW3E/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXOMOHE37A6LS4ZXLA3FEDNW3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E/action/storage_attestation","attest_author":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E/action/author_attestation","sign_citation":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E/action/citation_signature","submit_replication":"https://pith.science/pith/ZXOMOHE37A6LS4ZXLA3FEDNW3E/action/replication_record"}},"created_at":"2026-07-05T02:06:28.612453+00:00","updated_at":"2026-07-05T02:06:28.612453+00:00"}