{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UYEKE6J27263S677KTKG3GDEZ5","short_pith_number":"pith:UYEKE6J2","schema_version":"1.0","canonical_sha256":"a608a2793afebdb97bff54d46d9864cf6b1e12150b70c2be1222f0acbe8c2528","source":{"kind":"arxiv","id":"2505.23036","version":1},"attestation_state":"computed","paper":{"title":"AISHELL-5: The First Open-Source In-Car Multi-Channel Multi-Speaker Speech Dataset for Automatic Speech Diarization and Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"He Wang, Hongxiao Guo, Hui Bu, Lei Xie, Shaoji Zhang, Shuiyuan Wang, Wei Chen, Xingchen Li, Xin Xu, Yuhang Dai, Zihan Zhang","submitted_at":"2025-05-29T03:22:59Z","abstract_excerpt":"This paper delineates AISHELL-5, the first open-source in-car multi-channel multi-speaker Mandarin automatic speech recognition (ASR) dataset. AISHLL-5 includes two parts: (1) over 100 hours of multi-channel speech data recorded in an electric vehicle across more than 60 real driving scenarios. This audio data consists of four far-field speech signals captured by microphones located on each car door, as well as near-field signals obtained from high-fidelity headset microphones worn by each speaker. (2) a collection of 40 hours of real-world environmental noise recordings, which supports the in"},"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":"2505.23036","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T03:22:59Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8109941dbfba82d3467675c3f2cd3e35dde58abdeb10dea6176dadda241f2807","abstract_canon_sha256":"4a7c3807e80a38ec459a72787ff2e520fe04673580e50b6acb18cd426d61cacf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:11.897110Z","signature_b64":"yKbm7mgzPzLELwhcXMminEvFyEQ3M9bZTv/52SBqnMSHUQPZbhGo8IaRPq953vVKPN4AuSqoiyJ8R8slm6hmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a608a2793afebdb97bff54d46d9864cf6b1e12150b70c2be1222f0acbe8c2528","last_reissued_at":"2026-07-05T11:12:11.896640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:11.896640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AISHELL-5: The First Open-Source In-Car Multi-Channel Multi-Speaker Speech Dataset for Automatic Speech Diarization and Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"He Wang, Hongxiao Guo, Hui Bu, Lei Xie, Shaoji Zhang, Shuiyuan Wang, Wei Chen, Xingchen Li, Xin Xu, Yuhang Dai, Zihan Zhang","submitted_at":"2025-05-29T03:22:59Z","abstract_excerpt":"This paper delineates AISHELL-5, the first open-source in-car multi-channel multi-speaker Mandarin automatic speech recognition (ASR) dataset. AISHLL-5 includes two parts: (1) over 100 hours of multi-channel speech data recorded in an electric vehicle across more than 60 real driving scenarios. This audio data consists of four far-field speech signals captured by microphones located on each car door, as well as near-field signals obtained from high-fidelity headset microphones worn by each speaker. (2) a collection of 40 hours of real-world environmental noise recordings, which supports the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23036","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/2505.23036/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":"2505.23036","created_at":"2026-07-05T11:12:11.896692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23036v1","created_at":"2026-07-05T11:12:11.896692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23036","created_at":"2026-07-05T11:12:11.896692+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYEKE6J27263","created_at":"2026-07-05T11:12:11.896692+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYEKE6J27263S677","created_at":"2026-07-05T11:12:11.896692+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYEKE6J2","created_at":"2026-07-05T11:12:11.896692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30899","citing_title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":167,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5","json":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5.json","graph_json":"https://pith.science/api/pith-number/UYEKE6J27263S677KTKG3GDEZ5/graph.json","events_json":"https://pith.science/api/pith-number/UYEKE6J27263S677KTKG3GDEZ5/events.json","paper":"https://pith.science/paper/UYEKE6J2"},"agent_actions":{"view_html":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5","download_json":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5.json","view_paper":"https://pith.science/paper/UYEKE6J2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23036&json=true","fetch_graph":"https://pith.science/api/pith-number/UYEKE6J27263S677KTKG3GDEZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/UYEKE6J27263S677KTKG3GDEZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5/action/storage_attestation","attest_author":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5/action/author_attestation","sign_citation":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5/action/citation_signature","submit_replication":"https://pith.science/pith/UYEKE6J27263S677KTKG3GDEZ5/action/replication_record"}},"created_at":"2026-07-05T11:12:11.896692+00:00","updated_at":"2026-07-05T11:12:11.896692+00:00"}