{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PHM4PZIW45CI6YUNRJ47L2ARC2","short_pith_number":"pith:PHM4PZIW","schema_version":"1.0","canonical_sha256":"79d9c7e516e7448f628d8a79f5e81116a928682a8be70faacb542b7978e28d97","source":{"kind":"arxiv","id":"2108.01129","version":1},"attestation_state":"computed","paper":{"title":"Decoupling recognition and transcription in Mandarin ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongji Gao, Jiahong Yuan, Kenneth Church, Liang Huang, Renjie Zheng, Xingyu Cai","submitted_at":"2021-08-02T19:09:41Z","abstract_excerpt":"Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach. Unlike English where the writing system is closely related to sound, Chinese characters (Hanzi) represent meaning, not sound. We propose factoring audio -> Hanzi into two sub-tasks: (1) audio -> Pinyin and (2) Pinyin -> Hanzi, where Pinyin is a system of phonetic transcription of standard Chinese. Factoring the audio -> Hanzi task in this way achieves 3.9% CER (character error rate) on the Aishell-1 corpus, the best result reported on this dataset so far."},"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":"2108.01129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:09:41Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"48e40298b5513fa0213ab1231c40a275d39df0a041ced515c1eb16d94aef7651","abstract_canon_sha256":"b133a8e33c924a7b37ac4a06b58c805642423fb326ad24fd32561a319c627cae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:59.803001Z","signature_b64":"yRPN5uivZ58RyVZeL66I+wKQHxrWCNouQ6dWyR5dgilVj+0cM2vUwcqaUSC4k5K8S/MjL9XwUNuCw7MuiebyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79d9c7e516e7448f628d8a79f5e81116a928682a8be70faacb542b7978e28d97","last_reissued_at":"2026-07-05T03:02:59.802647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:59.802647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling recognition and transcription in Mandarin ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongji Gao, Jiahong Yuan, Kenneth Church, Liang Huang, Renjie Zheng, Xingyu Cai","submitted_at":"2021-08-02T19:09:41Z","abstract_excerpt":"Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach. Unlike English where the writing system is closely related to sound, Chinese characters (Hanzi) represent meaning, not sound. We propose factoring audio -> Hanzi into two sub-tasks: (1) audio -> Pinyin and (2) Pinyin -> Hanzi, where Pinyin is a system of phonetic transcription of standard Chinese. Factoring the audio -> Hanzi task in this way achieves 3.9% CER (character error rate) on the Aishell-1 corpus, the best result reported on this dataset so far."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01129","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/2108.01129/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":"2108.01129","created_at":"2026-07-05T03:02:59.802705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01129v1","created_at":"2026-07-05T03:02:59.802705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01129","created_at":"2026-07-05T03:02:59.802705+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHM4PZIW45CI","created_at":"2026-07-05T03:02:59.802705+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHM4PZIW45CI6YUN","created_at":"2026-07-05T03:02:59.802705+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHM4PZIW","created_at":"2026-07-05T03:02:59.802705+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/PHM4PZIW45CI6YUNRJ47L2ARC2","json":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2.json","graph_json":"https://pith.science/api/pith-number/PHM4PZIW45CI6YUNRJ47L2ARC2/graph.json","events_json":"https://pith.science/api/pith-number/PHM4PZIW45CI6YUNRJ47L2ARC2/events.json","paper":"https://pith.science/paper/PHM4PZIW"},"agent_actions":{"view_html":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2","download_json":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2.json","view_paper":"https://pith.science/paper/PHM4PZIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01129&json=true","fetch_graph":"https://pith.science/api/pith-number/PHM4PZIW45CI6YUNRJ47L2ARC2/graph.json","fetch_events":"https://pith.science/api/pith-number/PHM4PZIW45CI6YUNRJ47L2ARC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2/action/storage_attestation","attest_author":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2/action/author_attestation","sign_citation":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2/action/citation_signature","submit_replication":"https://pith.science/pith/PHM4PZIW45CI6YUNRJ47L2ARC2/action/replication_record"}},"created_at":"2026-07-05T03:02:59.802705+00:00","updated_at":"2026-07-05T03:02:59.802705+00:00"}