{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CUR7S4HCVGXSHWPGKEKNRWLRIU","short_pith_number":"pith:CUR7S4HC","schema_version":"1.0","canonical_sha256":"1523f970e2a9af23d9e65114d8d971452b883e412cc531d73bbf351a03150fe0","source":{"kind":"arxiv","id":"1709.05522","version":1},"attestation_state":"computed","paper":{"title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bengu Wu, Hao Zheng, Hui Bu, Jiayu Du, Xingyu Na","submitted_at":"2017-09-16T14:33:27Z","abstract_excerpt":"An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the largest corpus which is suitable for conducting the speech recognition research and building speech recognition systems for Mandarin. The recording procedure, including audio capturing devices and environments are presented in details. The preparation of the related resources, including transcriptions and lexicon are described. The corpus is released with a Kaldi recipe. Experimental results implies that the quality of audio recordings and transcriptions are promising."},"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":"1709.05522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-16T14:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"a6468ebcf7d07c05d68f946147fe29e9b38f576626b005d546ebbb6d82b5cc92","abstract_canon_sha256":"fdce81a56c4394ba9ab1b466df390c53ceffbc4870b65a90d1cb595d8b43ea60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:00.465657Z","signature_b64":"8M0OPmqffkFhzOT4rEEe/WQWgFLI7GJjZMWABSsde7RUIPKqMuB6rEBbnuinNKGY08tJrNAGZL/CwQTaAYbHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1523f970e2a9af23d9e65114d8d971452b883e412cc531d73bbf351a03150fe0","last_reissued_at":"2026-05-18T00:35:00.464951Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:00.464951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bengu Wu, Hao Zheng, Hui Bu, Jiayu Du, Xingyu Na","submitted_at":"2017-09-16T14:33:27Z","abstract_excerpt":"An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the largest corpus which is suitable for conducting the speech recognition research and building speech recognition systems for Mandarin. The recording procedure, including audio capturing devices and environments are presented in details. The preparation of the related resources, including transcriptions and lexicon are described. The corpus is released with a Kaldi recipe. Experimental results implies that the quality of audio recordings and transcriptions are promising."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05522","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":""},"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":"1709.05522","created_at":"2026-05-18T00:35:00.465060+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.05522v1","created_at":"2026-05-18T00:35:00.465060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05522","created_at":"2026-05-18T00:35:00.465060+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUR7S4HCVGXS","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUR7S4HCVGXSHWPG","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUR7S4HC","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.28139","citing_title":"Data-Efficient On-Policy Distillation for Automatic Speech Recognition","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":135,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU","json":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU.json","graph_json":"https://pith.science/api/pith-number/CUR7S4HCVGXSHWPGKEKNRWLRIU/graph.json","events_json":"https://pith.science/api/pith-number/CUR7S4HCVGXSHWPGKEKNRWLRIU/events.json","paper":"https://pith.science/paper/CUR7S4HC"},"agent_actions":{"view_html":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU","download_json":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU.json","view_paper":"https://pith.science/paper/CUR7S4HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.05522&json=true","fetch_graph":"https://pith.science/api/pith-number/CUR7S4HCVGXSHWPGKEKNRWLRIU/graph.json","fetch_events":"https://pith.science/api/pith-number/CUR7S4HCVGXSHWPGKEKNRWLRIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU/action/storage_attestation","attest_author":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU/action/author_attestation","sign_citation":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU/action/citation_signature","submit_replication":"https://pith.science/pith/CUR7S4HCVGXSHWPGKEKNRWLRIU/action/replication_record"}},"created_at":"2026-05-18T00:35:00.465060+00:00","updated_at":"2026-05-18T00:35:00.465060+00:00"}