{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M6ORLSIF6LEPGHFR5B4KLP4KOB","short_pith_number":"pith:M6ORLSIF","schema_version":"1.0","canonical_sha256":"679d15c905f2c8f31cb1e878a5bf8a704f808ba51c44d114f3be0414fe1e9c81","source":{"kind":"arxiv","id":"2011.02160","version":2},"attestation_state":"computed","paper":{"title":"Data Augmentation for End-to-end Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenpeng Du, Hao Li, Lan Wang, Yanmin Qian, Yizhou Lu","submitted_at":"2020-11-04T07:12:44Z","abstract_excerpt":"Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data augmentation. Specifically, they are audio splicing with the existing code-switching data, and TTS with new code-switching texts generated by word translation or word insertion. Our experiments on 200 hours Mandarin-English code-switching dataset show that all the three proposed approaches yield significant improvements on code-switching ASR individually. Mor"},"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":"2011.02160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T07:12:44Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b474f87237b87cae9f2a10218b648c26426a74cce7705bf378618d2e7cba0e4e","abstract_canon_sha256":"34dd029eb525b719b0fed29384d44d9faa450718cd8f96710e64e5de341748d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:00.212432Z","signature_b64":"dYmuywTDnFz7hRUfVYN5nYR/G03CusbQZTxFlGUMj0Jw6glpXLvFDm2gk4TdR5W/RSsYowWi3bCFGxaEgKOLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"679d15c905f2c8f31cb1e878a5bf8a704f808ba51c44d114f3be0414fe1e9c81","last_reissued_at":"2026-07-05T09:30:00.211996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:00.211996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation for End-to-end Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenpeng Du, Hao Li, Lan Wang, Yanmin Qian, Yizhou Lu","submitted_at":"2020-11-04T07:12:44Z","abstract_excerpt":"Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data augmentation. Specifically, they are audio splicing with the existing code-switching data, and TTS with new code-switching texts generated by word translation or word insertion. Our experiments on 200 hours Mandarin-English code-switching dataset show that all the three proposed approaches yield significant improvements on code-switching ASR individually. Mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02160","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/2011.02160/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":"2011.02160","created_at":"2026-07-05T09:30:00.212051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02160v2","created_at":"2026-07-05T09:30:00.212051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02160","created_at":"2026-07-05T09:30:00.212051+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6ORLSIF6LEP","created_at":"2026-07-05T09:30:00.212051+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6ORLSIF6LEPGHFR","created_at":"2026-07-05T09:30:00.212051+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6ORLSIF","created_at":"2026-07-05T09:30:00.212051+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/M6ORLSIF6LEPGHFR5B4KLP4KOB","json":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB.json","graph_json":"https://pith.science/api/pith-number/M6ORLSIF6LEPGHFR5B4KLP4KOB/graph.json","events_json":"https://pith.science/api/pith-number/M6ORLSIF6LEPGHFR5B4KLP4KOB/events.json","paper":"https://pith.science/paper/M6ORLSIF"},"agent_actions":{"view_html":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB","download_json":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB.json","view_paper":"https://pith.science/paper/M6ORLSIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02160&json=true","fetch_graph":"https://pith.science/api/pith-number/M6ORLSIF6LEPGHFR5B4KLP4KOB/graph.json","fetch_events":"https://pith.science/api/pith-number/M6ORLSIF6LEPGHFR5B4KLP4KOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB/action/storage_attestation","attest_author":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB/action/author_attestation","sign_citation":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB/action/citation_signature","submit_replication":"https://pith.science/pith/M6ORLSIF6LEPGHFR5B4KLP4KOB/action/replication_record"}},"created_at":"2026-07-05T09:30:00.212051+00:00","updated_at":"2026-07-05T09:30:00.212051+00:00"}