{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WUKJ2V37S6LL5XNCRY7CR7JNT4","short_pith_number":"pith:WUKJ2V37","schema_version":"1.0","canonical_sha256":"b5149d577f9796bedda28e3e28fd2d9f2974b78d56b27bd588984c6072e11bcf","source":{"kind":"arxiv","id":"1808.10583","version":2},"attestation_state":"computed","paper":{"title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Bu, Jiayu Du, Xingyu Na, Xuechen Liu","submitted_at":"2018-08-31T03:11:08Z","abstract_excerpt":"AISHELL-1 is by far the largest open-source speech corpus available for Mandarin speech recognition research. It was released with a baseline system containing solid training and testing pipelines for Mandarin ASR. In AISHELL-2, 1000 hours of clean read-speech data from iOS is published, which is free for academic usage. On top of AISHELL-2 corpus, an improved recipe is developed and released, containing key components for industrial applications, such as Chinese word segmentation, flexible vocabulary expension and phone set transformation etc. Pipelines support various state-of-the-art techni"},"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":"1808.10583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-31T03:11:08Z","cross_cats_sorted":[],"title_canon_sha256":"19639c0acc5b658bd2e7959d6bfd03ab4d4486a83dce2bfadb788e025300ceb8","abstract_canon_sha256":"a209e7ffbc65571c46cd8d489d2bfbb72f6998ad8b2bccd988a77f48091d1ada"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:50.368720Z","signature_b64":"oU896O9u0vcDqXbFN3YFd8m86UynhRqMbgZKYgzf5y8wT/nJMfMF8VebiqjfaurLXfhSuS5kHS4oJolcZFtwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5149d577f9796bedda28e3e28fd2d9f2974b78d56b27bd588984c6072e11bcf","last_reissued_at":"2026-05-18T00:05:50.368155Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:50.368155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Bu, Jiayu Du, Xingyu Na, Xuechen Liu","submitted_at":"2018-08-31T03:11:08Z","abstract_excerpt":"AISHELL-1 is by far the largest open-source speech corpus available for Mandarin speech recognition research. It was released with a baseline system containing solid training and testing pipelines for Mandarin ASR. In AISHELL-2, 1000 hours of clean read-speech data from iOS is published, which is free for academic usage. On top of AISHELL-2 corpus, an improved recipe is developed and released, containing key components for industrial applications, such as Chinese word segmentation, flexible vocabulary expension and phone set transformation etc. Pipelines support various state-of-the-art techni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10583","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":""},"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":"1808.10583","created_at":"2026-05-18T00:05:50.368245+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.10583v2","created_at":"2026-05-18T00:05:50.368245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10583","created_at":"2026-05-18T00:05:50.368245+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUKJ2V37S6LL","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUKJ2V37S6LL5XNC","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUKJ2V37","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.23463","citing_title":"StepAudio 2.5 Technical Report","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":159,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01897","citing_title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07919","citing_title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27393","citing_title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18105","citing_title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08003","citing_title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2407.10759","citing_title":"Qwen2-Audio Technical Report","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4","json":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4.json","graph_json":"https://pith.science/api/pith-number/WUKJ2V37S6LL5XNCRY7CR7JNT4/graph.json","events_json":"https://pith.science/api/pith-number/WUKJ2V37S6LL5XNCRY7CR7JNT4/events.json","paper":"https://pith.science/paper/WUKJ2V37"},"agent_actions":{"view_html":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4","download_json":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4.json","view_paper":"https://pith.science/paper/WUKJ2V37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.10583&json=true","fetch_graph":"https://pith.science/api/pith-number/WUKJ2V37S6LL5XNCRY7CR7JNT4/graph.json","fetch_events":"https://pith.science/api/pith-number/WUKJ2V37S6LL5XNCRY7CR7JNT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4/action/storage_attestation","attest_author":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4/action/author_attestation","sign_citation":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4/action/citation_signature","submit_replication":"https://pith.science/pith/WUKJ2V37S6LL5XNCRY7CR7JNT4/action/replication_record"}},"created_at":"2026-05-18T00:05:50.368245+00:00","updated_at":"2026-05-18T00:05:50.368245+00:00"}