{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:M6ORLSIF6LEPGHFR5B4KLP4KOB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"34dd029eb525b719b0fed29384d44d9faa450718cd8f96710e64e5de341748d9","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T07:12:44Z","title_canon_sha256":"b474f87237b87cae9f2a10218b648c26426a74cce7705bf378618d2e7cba0e4e"},"schema_version":"1.0","source":{"id":"2011.02160","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02160","created_at":"2026-07-05T09:30:00Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02160v2","created_at":"2026-07-05T09:30:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02160","created_at":"2026-07-05T09:30:00Z"},{"alias_kind":"pith_short_12","alias_value":"M6ORLSIF6LEP","created_at":"2026-07-05T09:30:00Z"},{"alias_kind":"pith_short_16","alias_value":"M6ORLSIF6LEPGHFR","created_at":"2026-07-05T09:30:00Z"},{"alias_kind":"pith_short_8","alias_value":"M6ORLSIF","created_at":"2026-07-05T09:30:00Z"}],"graph_snapshots":[{"event_id":"sha256:0589c9d85f7e6ab3cbbb6d44292099aa212dd5243f2846d43b28a92ea656d1b8","target":"graph","created_at":"2026-07-05T09:30:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.02160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenpeng Du, Hao Li, Lan Wang, Yanmin Qian, Yizhou Lu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T07:12:44Z","title":"Data Augmentation for End-to-end Code-switching Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02160","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c44885d76443c7230a1b2a9671c2f554dbe78b73c460173f7c6d3db7b7d7b950","target":"record","created_at":"2026-07-05T09:30:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"34dd029eb525b719b0fed29384d44d9faa450718cd8f96710e64e5de341748d9","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T07:12:44Z","title_canon_sha256":"b474f87237b87cae9f2a10218b648c26426a74cce7705bf378618d2e7cba0e4e"},"schema_version":"1.0","source":{"id":"2011.02160","kind":"arxiv","version":2}},"canonical_sha256":"679d15c905f2c8f31cb1e878a5bf8a704f808ba51c44d114f3be0414fe1e9c81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"679d15c905f2c8f31cb1e878a5bf8a704f808ba51c44d114f3be0414fe1e9c81","first_computed_at":"2026-07-05T09:30:00.211996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:00.211996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dYmuywTDnFz7hRUfVYN5nYR/G03CusbQZTxFlGUMj0Jw6glpXLvFDm2gk4TdR5W/RSsYowWi3bCFGxaEgKOLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:00.212432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02160","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c44885d76443c7230a1b2a9671c2f554dbe78b73c460173f7c6d3db7b7d7b950","sha256:0589c9d85f7e6ab3cbbb6d44292099aa212dd5243f2846d43b28a92ea656d1b8"],"state_sha256":"3eae1e36e2dd7dc9ddb7065a96ebfc063b8a7b2a46e3101c554f5cb6125e8fce"}