{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FRJOQFD5VRGINJPTZ6PGXW3Q2W","short_pith_number":"pith:FRJOQFD5","schema_version":"1.0","canonical_sha256":"2c52e8147dac4c86a5f3cf9e6bdb70d5bcd103cc196c7e7752479e69d4037d1c","source":{"kind":"arxiv","id":"2211.12433","version":2},"attestation_state":"computed","paper":{"title":"TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Byeong-Yeol Kim, Samuele Cornell, Shinji Watanabe, Shukjae Choi, Younglo Lee, Zhong-Qiu Wang","submitted_at":"2022-11-22T17:43:12Z","abstract_excerpt":"We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band module, a sub-band temporal module, and a cross-frame self-attention module. It is trained to perform complex spectral mapping, where the real and imaginary (RI) components of input signals are stacked as features to predict target RI components. We first evaluate it on monaural anechoic speaker separation. Without using data augmentation and dynamic mixing, 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":"2211.12433","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-22T17:43:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"991cf01f8a683af6533d8a2b50bc5d92a64c3034cb3a5dbbe52fd7a26d7d26e2","abstract_canon_sha256":"4c38c824c3beba54c8460439127f25b15b1a5d16283dbe567b167fec02b1edad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:42.858695Z","signature_b64":"Xmnk+KYB6oISmHdvXRu4IEsJBbKtUuDbUPzMaKpEwRDq3OY4Yy0EKLMf90O1erU+O+a9hkUiB2WwZi3o/o/XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c52e8147dac4c86a5f3cf9e6bdb70d5bcd103cc196c7e7752479e69d4037d1c","last_reissued_at":"2026-07-05T06:37:42.858219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:42.858219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Byeong-Yeol Kim, Samuele Cornell, Shinji Watanabe, Shukjae Choi, Younglo Lee, Zhong-Qiu Wang","submitted_at":"2022-11-22T17:43:12Z","abstract_excerpt":"We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band module, a sub-band temporal module, and a cross-frame self-attention module. It is trained to perform complex spectral mapping, where the real and imaginary (RI) components of input signals are stacked as features to predict target RI components. We first evaluate it on monaural anechoic speaker separation. Without using data augmentation and dynamic mixing, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12433","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/2211.12433/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":"2211.12433","created_at":"2026-07-05T06:37:42.858272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12433v2","created_at":"2026-07-05T06:37:42.858272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12433","created_at":"2026-07-05T06:37:42.858272+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRJOQFD5VRGI","created_at":"2026-07-05T06:37:42.858272+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRJOQFD5VRGINJPT","created_at":"2026-07-05T06:37:42.858272+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRJOQFD5","created_at":"2026-07-05T06:37:42.858272+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/FRJOQFD5VRGINJPTZ6PGXW3Q2W","json":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W.json","graph_json":"https://pith.science/api/pith-number/FRJOQFD5VRGINJPTZ6PGXW3Q2W/graph.json","events_json":"https://pith.science/api/pith-number/FRJOQFD5VRGINJPTZ6PGXW3Q2W/events.json","paper":"https://pith.science/paper/FRJOQFD5"},"agent_actions":{"view_html":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W","download_json":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W.json","view_paper":"https://pith.science/paper/FRJOQFD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12433&json=true","fetch_graph":"https://pith.science/api/pith-number/FRJOQFD5VRGINJPTZ6PGXW3Q2W/graph.json","fetch_events":"https://pith.science/api/pith-number/FRJOQFD5VRGINJPTZ6PGXW3Q2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W/action/storage_attestation","attest_author":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W/action/author_attestation","sign_citation":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W/action/citation_signature","submit_replication":"https://pith.science/pith/FRJOQFD5VRGINJPTZ6PGXW3Q2W/action/replication_record"}},"created_at":"2026-07-05T06:37:42.858272+00:00","updated_at":"2026-07-05T06:37:42.858272+00:00"}