{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EQMZDJCH2FZE5W5G4S3VN3TRKT","short_pith_number":"pith:EQMZDJCH","schema_version":"1.0","canonical_sha256":"241991a447d1724edba6e4b756ee7154c82f5364c6b879ecb89643058815acf8","source":{"kind":"arxiv","id":"2007.05916","version":1},"attestation_state":"computed","paper":{"title":"The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Lei Xie, Qiangze Feng, Xian Shi","submitted_at":"2020-07-12T05:38:57Z","abstract_excerpt":"Code-switching (CS) is a common phenomenon and recognizing CS speech is challenging. But CS speech data is scarce and there' s no common testbed in relevant research. This paper describes the design and main outcomes of the ASRU 2019 Mandarin-English code-switching speech recognition challenge, which aims to improve the ASR performance in Mandarin-English code-switching situation. 500 hours Mandarin speech data and 240 hours Mandarin-English intra-sentencial CS data are released to the participants. Three tracks were set for advancing the AM and LM part in traditional DNN-HMM ASR system, as we"},"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":"2007.05916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-12T05:38:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"64016cac5179322c1c2d1201e5f66b76c768e3e4e8c57867a122f4b5807e88e1","abstract_canon_sha256":"16cdbd55433d34d1877069da3df8811ca530b9a07113d41c4fb2582016a01d52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:08.082553Z","signature_b64":"+KT2DNgF1wi0TcMJMsEjHGe72PUDV8kM1PNDZEAqZH+ht7guvOPbtIuOVizkr9Mgkg8yypS5un2ydJnQ1nwXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241991a447d1724edba6e4b756ee7154c82f5364c6b879ecb89643058815acf8","last_reissued_at":"2026-07-05T01:18:08.082139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:08.082139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Lei Xie, Qiangze Feng, Xian Shi","submitted_at":"2020-07-12T05:38:57Z","abstract_excerpt":"Code-switching (CS) is a common phenomenon and recognizing CS speech is challenging. But CS speech data is scarce and there' s no common testbed in relevant research. This paper describes the design and main outcomes of the ASRU 2019 Mandarin-English code-switching speech recognition challenge, which aims to improve the ASR performance in Mandarin-English code-switching situation. 500 hours Mandarin speech data and 240 hours Mandarin-English intra-sentencial CS data are released to the participants. Three tracks were set for advancing the AM and LM part in traditional DNN-HMM ASR system, as we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05916","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.05916/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":"2007.05916","created_at":"2026-07-05T01:18:08.082197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.05916v1","created_at":"2026-07-05T01:18:08.082197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05916","created_at":"2026-07-05T01:18:08.082197+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQMZDJCH2FZE","created_at":"2026-07-05T01:18:08.082197+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQMZDJCH2FZE5W5G","created_at":"2026-07-05T01:18:08.082197+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQMZDJCH","created_at":"2026-07-05T01:18:08.082197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05846","citing_title":"Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01016","citing_title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09121","citing_title":"Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT","json":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT.json","graph_json":"https://pith.science/api/pith-number/EQMZDJCH2FZE5W5G4S3VN3TRKT/graph.json","events_json":"https://pith.science/api/pith-number/EQMZDJCH2FZE5W5G4S3VN3TRKT/events.json","paper":"https://pith.science/paper/EQMZDJCH"},"agent_actions":{"view_html":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT","download_json":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT.json","view_paper":"https://pith.science/paper/EQMZDJCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.05916&json=true","fetch_graph":"https://pith.science/api/pith-number/EQMZDJCH2FZE5W5G4S3VN3TRKT/graph.json","fetch_events":"https://pith.science/api/pith-number/EQMZDJCH2FZE5W5G4S3VN3TRKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT/action/storage_attestation","attest_author":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT/action/author_attestation","sign_citation":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT/action/citation_signature","submit_replication":"https://pith.science/pith/EQMZDJCH2FZE5W5G4S3VN3TRKT/action/replication_record"}},"created_at":"2026-07-05T01:18:08.082197+00:00","updated_at":"2026-07-05T01:18:08.082197+00:00"}