{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KYIPMRA7A2IHRJTITMPK2X2SOX","short_pith_number":"pith:KYIPMRA7","schema_version":"1.0","canonical_sha256":"5610f6441f069078a6689b1ead5f5275e5fc7bc901bd79160be72302ed34d053","source":{"kind":"arxiv","id":"2307.16516","version":2},"attestation_state":"computed","paper":{"title":"SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Changsheng Quan, Xiaofei Li","submitted_at":"2023-07-31T09:32:21Z","abstract_excerpt":"This work proposes a neural network to extensively exploit spatial information for multichannel joint speech separation, denoising and dereverberation, named SpatialNet. In the short-time Fourier transform (STFT) domain, the proposed network performs end-to-end speech enhancement. It is mainly composed of interleaved narrow-band and cross-band blocks to respectively exploit narrow-band and cross-band spatial information. The narrow-band blocks process frequencies independently, and use self-attention mechanism and temporal convolutional layers to respectively perform spatial-feature-based spea"},"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":"2307.16516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T09:32:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"838619b42216ae6399ee19624f82578dd65c44dff645fb445cf158694654ff91","abstract_canon_sha256":"30a76cd62d2bb35fff5c906fe221e60a5ff4770fdeaa86a0f8e899c319449b49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:07.439045Z","signature_b64":"UteFkh4wMdE7uqojn6p+SAFE0P/6poY1P2N9xQ4TPS9Sh366ypJzIW1+idsFfDtnWyIzVewp1GnO2EhHTdOgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5610f6441f069078a6689b1ead5f5275e5fc7bc901bd79160be72302ed34d053","last_reissued_at":"2026-07-05T07:27:07.438506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:07.438506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Changsheng Quan, Xiaofei Li","submitted_at":"2023-07-31T09:32:21Z","abstract_excerpt":"This work proposes a neural network to extensively exploit spatial information for multichannel joint speech separation, denoising and dereverberation, named SpatialNet. In the short-time Fourier transform (STFT) domain, the proposed network performs end-to-end speech enhancement. It is mainly composed of interleaved narrow-band and cross-band blocks to respectively exploit narrow-band and cross-band spatial information. The narrow-band blocks process frequencies independently, and use self-attention mechanism and temporal convolutional layers to respectively perform spatial-feature-based spea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16516","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/2307.16516/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":"2307.16516","created_at":"2026-07-05T07:27:07.438580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16516v2","created_at":"2026-07-05T07:27:07.438580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16516","created_at":"2026-07-05T07:27:07.438580+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYIPMRA7A2IH","created_at":"2026-07-05T07:27:07.438580+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYIPMRA7A2IHRJTI","created_at":"2026-07-05T07:27:07.438580+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYIPMRA7","created_at":"2026-07-05T07:27:07.438580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05657","citing_title":"ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX","json":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX.json","graph_json":"https://pith.science/api/pith-number/KYIPMRA7A2IHRJTITMPK2X2SOX/graph.json","events_json":"https://pith.science/api/pith-number/KYIPMRA7A2IHRJTITMPK2X2SOX/events.json","paper":"https://pith.science/paper/KYIPMRA7"},"agent_actions":{"view_html":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX","download_json":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX.json","view_paper":"https://pith.science/paper/KYIPMRA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16516&json=true","fetch_graph":"https://pith.science/api/pith-number/KYIPMRA7A2IHRJTITMPK2X2SOX/graph.json","fetch_events":"https://pith.science/api/pith-number/KYIPMRA7A2IHRJTITMPK2X2SOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX/action/storage_attestation","attest_author":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX/action/author_attestation","sign_citation":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX/action/citation_signature","submit_replication":"https://pith.science/pith/KYIPMRA7A2IHRJTITMPK2X2SOX/action/replication_record"}},"created_at":"2026-07-05T07:27:07.438580+00:00","updated_at":"2026-07-05T07:27:07.438580+00:00"}