{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3SGNRY62OYRV36OQYANYILSA4E","short_pith_number":"pith:3SGNRY62","schema_version":"1.0","canonical_sha256":"dc8cd8e3da76235df9d0c01b842e40e119f5cd3c8758ebc29130e2eac12ecd6d","source":{"kind":"arxiv","id":"2409.02041","version":2},"attestation_state":"computed","paper":{"title":"The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Di Cai, Feng Ma, Gaobin Yang, Genshun Wan, Guolong Zhong, Haitao Xu, Huaxin Wu, Jianqing Gao, Jia Pan, Jieru Chen, Jun Du, Mengzhi Wang, Ruoyu Wang, Shuangqing Qian, Shutong Niu, Siyuan Wu, Tian Gao, Xindi Yu, Xueyang Zhang, Yanhui Tu","submitted_at":"2024-09-03T16:42:07Z","abstract_excerpt":"This technical report outlines our submission system for the CHiME-8 NOTSOFAR-1 Challenge. The primary difficulty of this challenge is the dataset recorded across various conference rooms, which captures real-world complexities such as high overlap rates, background noises, a variable number of speakers, and natural conversation styles. To address these issues, we optimized the system in several aspects: For front-end speech signal processing, we introduced a data-driven joint training method for diarization and separation (JDS) to enhance audio quality. Additionally, we also integrated tradit"},"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":"2409.02041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-03T16:42:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ec3b6c04e8f458fe38bd638254d7c131f6d967984e96a129e7b50d4051600016","abstract_canon_sha256":"43c4e38c98622b3493fe53f550b6335f46c4ecc26c36db2148db00d860fc453f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:01.197306Z","signature_b64":"B3N0xgXLR1JpdrxGAN5FVu0CNEUcfjTeCngxMjnKvN7Zozb19moSdF7DsHLxzGttx+LIcdrEJlRarwnsleE0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc8cd8e3da76235df9d0c01b842e40e119f5cd3c8758ebc29130e2eac12ecd6d","last_reissued_at":"2026-07-05T09:25:01.196776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:01.196776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Di Cai, Feng Ma, Gaobin Yang, Genshun Wan, Guolong Zhong, Haitao Xu, Huaxin Wu, Jianqing Gao, Jia Pan, Jieru Chen, Jun Du, Mengzhi Wang, Ruoyu Wang, Shuangqing Qian, Shutong Niu, Siyuan Wu, Tian Gao, Xindi Yu, Xueyang Zhang, Yanhui Tu","submitted_at":"2024-09-03T16:42:07Z","abstract_excerpt":"This technical report outlines our submission system for the CHiME-8 NOTSOFAR-1 Challenge. The primary difficulty of this challenge is the dataset recorded across various conference rooms, which captures real-world complexities such as high overlap rates, background noises, a variable number of speakers, and natural conversation styles. To address these issues, we optimized the system in several aspects: For front-end speech signal processing, we introduced a data-driven joint training method for diarization and separation (JDS) to enhance audio quality. Additionally, we also integrated tradit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02041","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.02041/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":"2409.02041","created_at":"2026-07-05T09:25:01.196832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02041v2","created_at":"2026-07-05T09:25:01.196832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02041","created_at":"2026-07-05T09:25:01.196832+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SGNRY62OYRV","created_at":"2026-07-05T09:25:01.196832+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SGNRY62OYRV36OQ","created_at":"2026-07-05T09:25:01.196832+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SGNRY62","created_at":"2026-07-05T09:25:01.196832+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/3SGNRY62OYRV36OQYANYILSA4E","json":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E.json","graph_json":"https://pith.science/api/pith-number/3SGNRY62OYRV36OQYANYILSA4E/graph.json","events_json":"https://pith.science/api/pith-number/3SGNRY62OYRV36OQYANYILSA4E/events.json","paper":"https://pith.science/paper/3SGNRY62"},"agent_actions":{"view_html":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E","download_json":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E.json","view_paper":"https://pith.science/paper/3SGNRY62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02041&json=true","fetch_graph":"https://pith.science/api/pith-number/3SGNRY62OYRV36OQYANYILSA4E/graph.json","fetch_events":"https://pith.science/api/pith-number/3SGNRY62OYRV36OQYANYILSA4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E/action/storage_attestation","attest_author":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E/action/author_attestation","sign_citation":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E/action/citation_signature","submit_replication":"https://pith.science/pith/3SGNRY62OYRV36OQYANYILSA4E/action/replication_record"}},"created_at":"2026-07-05T09:25:01.196832+00:00","updated_at":"2026-07-05T09:25:01.196832+00:00"}