{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6HVIGXMOQDIBECA34XZI67FLKN","short_pith_number":"pith:6HVIGXMO","schema_version":"1.0","canonical_sha256":"f1ea835d8e80d012081be5f28f7cab535cf051472a682456846386d384960acc","source":{"kind":"arxiv","id":"2109.04049","version":1},"attestation_state":"computed","paper":{"title":"BeamTransformer: Microphone Array-based Overlapping Speech Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongbin Suo, Jinwei Feng, Ming Lei, Qian Chen, Shiliang Zhang, Siqi Zheng, Weilong Huang, Zhijie Yan","submitted_at":"2021-09-09T06:10:48Z","abstract_excerpt":"We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling. BeamTransformer seeks to optimize modeling of sequential relationship among signals from different spatial direction. Overlapping speech detection is one of the tasks where such optimization is favorable. In this paper we effectively apply BeamTransformer to detect overlapping segments. Comparing to single-channel approach, BeamTransformer exceeds in learning to identify the relationship among different beam sequences and hence able"},"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":"2109.04049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-09-09T06:10:48Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5c8086b185567b6bf534c8d15b70ca2730eeab58a539e9eca5c9c25ec7ab919a","abstract_canon_sha256":"9805b3c40f983a668cea3635bf26e1f4eea73e7f85008f46788779bc212d2693"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:54.191656Z","signature_b64":"a6qK5/yLx4POSrq0h8Ur8+q7U9Hizv09sZ8uMFjkesKepUT/UuCQbzd8z6OLCyxgORhKlCJx/CAS2MFcE6DABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1ea835d8e80d012081be5f28f7cab535cf051472a682456846386d384960acc","last_reissued_at":"2026-07-05T03:12:54.191146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:54.191146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BeamTransformer: Microphone Array-based Overlapping Speech Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongbin Suo, Jinwei Feng, Ming Lei, Qian Chen, Shiliang Zhang, Siqi Zheng, Weilong Huang, Zhijie Yan","submitted_at":"2021-09-09T06:10:48Z","abstract_excerpt":"We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling. BeamTransformer seeks to optimize modeling of sequential relationship among signals from different spatial direction. Overlapping speech detection is one of the tasks where such optimization is favorable. In this paper we effectively apply BeamTransformer to detect overlapping segments. Comparing to single-channel approach, BeamTransformer exceeds in learning to identify the relationship among different beam sequences and hence able"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04049","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/2109.04049/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":"2109.04049","created_at":"2026-07-05T03:12:54.191205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04049v1","created_at":"2026-07-05T03:12:54.191205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04049","created_at":"2026-07-05T03:12:54.191205+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HVIGXMOQDIB","created_at":"2026-07-05T03:12:54.191205+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HVIGXMOQDIBECA3","created_at":"2026-07-05T03:12:54.191205+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HVIGXMO","created_at":"2026-07-05T03:12:54.191205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23207","citing_title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN","json":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN.json","graph_json":"https://pith.science/api/pith-number/6HVIGXMOQDIBECA34XZI67FLKN/graph.json","events_json":"https://pith.science/api/pith-number/6HVIGXMOQDIBECA34XZI67FLKN/events.json","paper":"https://pith.science/paper/6HVIGXMO"},"agent_actions":{"view_html":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN","download_json":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN.json","view_paper":"https://pith.science/paper/6HVIGXMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04049&json=true","fetch_graph":"https://pith.science/api/pith-number/6HVIGXMOQDIBECA34XZI67FLKN/graph.json","fetch_events":"https://pith.science/api/pith-number/6HVIGXMOQDIBECA34XZI67FLKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN/action/storage_attestation","attest_author":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN/action/author_attestation","sign_citation":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN/action/citation_signature","submit_replication":"https://pith.science/pith/6HVIGXMOQDIBECA34XZI67FLKN/action/replication_record"}},"created_at":"2026-07-05T03:12:54.191205+00:00","updated_at":"2026-07-05T03:12:54.191205+00:00"}