{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QUEFIFN33PKSSLVMRSJZ2JBB6K","short_pith_number":"pith:QUEFIFN3","schema_version":"1.0","canonical_sha256":"85085415bbdbd5292eac8c939d2421f296598b11cb76d2a867349b2c5c9ceec7","source":{"kind":"arxiv","id":"2212.03401","version":1},"attestation_state":"computed","paper":{"title":"MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyun Deng, Fei Wang, Gaoyan Zhang, Haoran Yin, Jianwu Dang, Longbiao Wang, Meng Ge, Yanjie Fu","submitted_at":"2022-12-07T01:52:40Z","abstract_excerpt":"Recently, many deep learning based beamformers have been proposed for multi-channel speech separation. Nevertheless, most of them rely on extra cues known in advance, such as speaker feature, face image or directional information. In this paper, we propose an end-to-end beamforming network for direction guided speech separation given merely the mixture signal, namely MIMO-DBnet. Specifically, we design a multi-channel input and multiple outputs architecture to predict the direction-of-arrival based embeddings and beamforming weights for each source. The precisely estimated directional embeddin"},"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":"2212.03401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-12-07T01:52:40Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"d796e8b562aedbfd9ea2e1ee7e6e97f77804c16f4fd444064cbeec38e534c472","abstract_canon_sha256":"a8218ee84a074d5cb912e549d633bd90a278177b97b29c237fda48a8aa139369"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:15.736431Z","signature_b64":"VlMEq2RSeeMAGpWADA2ZAGa2Tv2vHmBov1AoM1tMa6cwpX1G42aH9fgMDT8KxJzju1fOW6f2eBGu7VtVWDE3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85085415bbdbd5292eac8c939d2421f296598b11cb76d2a867349b2c5c9ceec7","last_reissued_at":"2026-07-05T05:23:15.736023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:15.736023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyun Deng, Fei Wang, Gaoyan Zhang, Haoran Yin, Jianwu Dang, Longbiao Wang, Meng Ge, Yanjie Fu","submitted_at":"2022-12-07T01:52:40Z","abstract_excerpt":"Recently, many deep learning based beamformers have been proposed for multi-channel speech separation. Nevertheless, most of them rely on extra cues known in advance, such as speaker feature, face image or directional information. In this paper, we propose an end-to-end beamforming network for direction guided speech separation given merely the mixture signal, namely MIMO-DBnet. Specifically, we design a multi-channel input and multiple outputs architecture to predict the direction-of-arrival based embeddings and beamforming weights for each source. The precisely estimated directional embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03401","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/2212.03401/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":"2212.03401","created_at":"2026-07-05T05:23:15.736082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.03401v1","created_at":"2026-07-05T05:23:15.736082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03401","created_at":"2026-07-05T05:23:15.736082+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUEFIFN33PKS","created_at":"2026-07-05T05:23:15.736082+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUEFIFN33PKSSLVM","created_at":"2026-07-05T05:23:15.736082+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUEFIFN3","created_at":"2026-07-05T05:23:15.736082+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/QUEFIFN33PKSSLVMRSJZ2JBB6K","json":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K.json","graph_json":"https://pith.science/api/pith-number/QUEFIFN33PKSSLVMRSJZ2JBB6K/graph.json","events_json":"https://pith.science/api/pith-number/QUEFIFN33PKSSLVMRSJZ2JBB6K/events.json","paper":"https://pith.science/paper/QUEFIFN3"},"agent_actions":{"view_html":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K","download_json":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K.json","view_paper":"https://pith.science/paper/QUEFIFN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.03401&json=true","fetch_graph":"https://pith.science/api/pith-number/QUEFIFN33PKSSLVMRSJZ2JBB6K/graph.json","fetch_events":"https://pith.science/api/pith-number/QUEFIFN33PKSSLVMRSJZ2JBB6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K/action/storage_attestation","attest_author":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K/action/author_attestation","sign_citation":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K/action/citation_signature","submit_replication":"https://pith.science/pith/QUEFIFN33PKSSLVMRSJZ2JBB6K/action/replication_record"}},"created_at":"2026-07-05T05:23:15.736082+00:00","updated_at":"2026-07-05T05:23:15.736082+00:00"}