{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4CTTLZFFLETYQTX4GC5RHMVION","short_pith_number":"pith:4CTTLZFF","schema_version":"1.0","canonical_sha256":"e0a735e4a55927884efc30bb13b2a8735c3392106d535f0e6073957707a1cc07","source":{"kind":"arxiv","id":"2506.16228","version":2},"attestation_state":"computed","paper":{"title":"Spatio-spectral diarization of meetings by combining TDOA-based segmentation and speaker embedding-based clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Marc Deegen, Reinhold Haeb-Umbach, Tobias Cord-Landwehr, Tobias Gburrek","submitted_at":"2025-06-19T11:37:35Z","abstract_excerpt":"We propose a spatio-spectral, combined model-based and data-driven diarization pipeline consisting of TDOA-based segmentation followed by embedding-based clustering. The proposed system requires neither access to multi-channel training data nor prior knowledge about the number or placement of microphones. It works for both a compact microphone array and distributed microphones, with minor adjustments. Due to its superior handling of overlapping speech during segmentation, the proposed pipeline significantly outperforms the single-channel pyannote approach, both in a scenario with a compact mic"},"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":"2506.16228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-19T11:37:35Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"52ef26cb1b21b981c8eae86b1c6819618cda871deafd72ab072b214bff105868","abstract_canon_sha256":"d02f881a212f3fb753e005890e5a22136b291855d6a7622bb0101bb3e06ec91d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:24.106079Z","signature_b64":"7daPpCVhs7uAg6VXYskbXpXLjxi+1S6GLW2o9vgh8pmO4XOAIB6l/iZ1lzvNLKC9aQ8Roc/LOUXWlYOpByBeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a735e4a55927884efc30bb13b2a8735c3392106d535f0e6073957707a1cc07","last_reissued_at":"2026-07-05T12:01:24.105574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:24.105574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatio-spectral diarization of meetings by combining TDOA-based segmentation and speaker embedding-based clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Marc Deegen, Reinhold Haeb-Umbach, Tobias Cord-Landwehr, Tobias Gburrek","submitted_at":"2025-06-19T11:37:35Z","abstract_excerpt":"We propose a spatio-spectral, combined model-based and data-driven diarization pipeline consisting of TDOA-based segmentation followed by embedding-based clustering. The proposed system requires neither access to multi-channel training data nor prior knowledge about the number or placement of microphones. It works for both a compact microphone array and distributed microphones, with minor adjustments. Due to its superior handling of overlapping speech during segmentation, the proposed pipeline significantly outperforms the single-channel pyannote approach, both in a scenario with a compact mic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16228","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/2506.16228/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":"2506.16228","created_at":"2026-07-05T12:01:24.105632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16228v2","created_at":"2026-07-05T12:01:24.105632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16228","created_at":"2026-07-05T12:01:24.105632+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CTTLZFFLETY","created_at":"2026-07-05T12:01:24.105632+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CTTLZFFLETYQTX4","created_at":"2026-07-05T12:01:24.105632+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CTTLZFF","created_at":"2026-07-05T12:01:24.105632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16228","citing_title":"Spatio-spectral diarization of meetings by combining TDOA-based segmentation and speaker embedding-based clustering","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION","json":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION.json","graph_json":"https://pith.science/api/pith-number/4CTTLZFFLETYQTX4GC5RHMVION/graph.json","events_json":"https://pith.science/api/pith-number/4CTTLZFFLETYQTX4GC5RHMVION/events.json","paper":"https://pith.science/paper/4CTTLZFF"},"agent_actions":{"view_html":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION","download_json":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION.json","view_paper":"https://pith.science/paper/4CTTLZFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16228&json=true","fetch_graph":"https://pith.science/api/pith-number/4CTTLZFFLETYQTX4GC5RHMVION/graph.json","fetch_events":"https://pith.science/api/pith-number/4CTTLZFFLETYQTX4GC5RHMVION/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION/action/storage_attestation","attest_author":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION/action/author_attestation","sign_citation":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION/action/citation_signature","submit_replication":"https://pith.science/pith/4CTTLZFFLETYQTX4GC5RHMVION/action/replication_record"}},"created_at":"2026-07-05T12:01:24.105632+00:00","updated_at":"2026-07-05T12:01:24.105632+00:00"}