{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HFIYTYIBNXQONDOLOHW4UC6P22","short_pith_number":"pith:HFIYTYIB","schema_version":"1.0","canonical_sha256":"395189e1016de0e68dcb71edca0bcfd6a7392d9b534cf42c8940cb999f696237","source":{"kind":"arxiv","id":"2509.01399","version":1},"attestation_state":"computed","paper":{"title":"CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-Car Speech Separation with Distributed Heterogeneous Arrays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Li Chen, Runduo Han, Yanxin Hu, Yihui Fu, Yukai Jv, Zihan Zhang","submitted_at":"2025-09-01T11:50:43Z","abstract_excerpt":"Separating overlapping speech from multiple speakers is crucial for effective human-vehicle interaction. This paper proposes CabinSep, a lightweight neural mask-based minimum variance distortionless response (MVDR) speech separation approach, to reduce speech recognition errors in back-end automatic speech recognition (ASR) models. Our contributions are threefold: First, we utilize channel information to extract spatial features, which improves the estimation of speech and noise masks. Second, we employ MVDR during inference, reducing speech distortion to make it more ASR-friendly. Third, we i"},"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":"2509.01399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-01T11:50:43Z","cross_cats_sorted":["cs.AI","cs.HC","eess.AS"],"title_canon_sha256":"a4bdd078630f982f012da872d3850a6b0f2145bd11d38cbc917486443593dd22","abstract_canon_sha256":"aa59e9e7b99c00a2249079a8b61fca6a1b027dcd2546417104477b7200e18a41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:59.825473Z","signature_b64":"w6+9xSt4izh33mX+nVU2v+HzBLzp2XtiOnE0zUl87ejvHSfvI2aidGxUMBZNjWM/BaRZhxSqnoPN0Rfb5D1gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"395189e1016de0e68dcb71edca0bcfd6a7392d9b534cf42c8940cb999f696237","last_reissued_at":"2026-07-05T12:02:59.824963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:59.824963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-Car Speech Separation with Distributed Heterogeneous Arrays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Li Chen, Runduo Han, Yanxin Hu, Yihui Fu, Yukai Jv, Zihan Zhang","submitted_at":"2025-09-01T11:50:43Z","abstract_excerpt":"Separating overlapping speech from multiple speakers is crucial for effective human-vehicle interaction. This paper proposes CabinSep, a lightweight neural mask-based minimum variance distortionless response (MVDR) speech separation approach, to reduce speech recognition errors in back-end automatic speech recognition (ASR) models. Our contributions are threefold: First, we utilize channel information to extract spatial features, which improves the estimation of speech and noise masks. Second, we employ MVDR during inference, reducing speech distortion to make it more ASR-friendly. Third, we i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01399","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/2509.01399/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":"2509.01399","created_at":"2026-07-05T12:02:59.825029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01399v1","created_at":"2026-07-05T12:02:59.825029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01399","created_at":"2026-07-05T12:02:59.825029+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFIYTYIBNXQO","created_at":"2026-07-05T12:02:59.825029+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFIYTYIBNXQONDOL","created_at":"2026-07-05T12:02:59.825029+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFIYTYIB","created_at":"2026-07-05T12:02:59.825029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01399","citing_title":"CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-Car Speech Separation with Distributed Heterogeneous Arrays","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22","json":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22.json","graph_json":"https://pith.science/api/pith-number/HFIYTYIBNXQONDOLOHW4UC6P22/graph.json","events_json":"https://pith.science/api/pith-number/HFIYTYIBNXQONDOLOHW4UC6P22/events.json","paper":"https://pith.science/paper/HFIYTYIB"},"agent_actions":{"view_html":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22","download_json":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22.json","view_paper":"https://pith.science/paper/HFIYTYIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01399&json=true","fetch_graph":"https://pith.science/api/pith-number/HFIYTYIBNXQONDOLOHW4UC6P22/graph.json","fetch_events":"https://pith.science/api/pith-number/HFIYTYIBNXQONDOLOHW4UC6P22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22/action/storage_attestation","attest_author":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22/action/author_attestation","sign_citation":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22/action/citation_signature","submit_replication":"https://pith.science/pith/HFIYTYIBNXQONDOLOHW4UC6P22/action/replication_record"}},"created_at":"2026-07-05T12:02:59.825029+00:00","updated_at":"2026-07-05T12:02:59.825029+00:00"}