{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OZPDOVBFENY3CPHGYLNAUNXLMM","short_pith_number":"pith:OZPDOVBF","schema_version":"1.0","canonical_sha256":"765e3754252371b13ce6c2da0a36eb63090a9addbe4b6d01eb223c1b9697cdc0","source":{"kind":"arxiv","id":"2107.05429","version":1},"attestation_state":"computed","paper":{"title":"DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongsheng Chen, Jing Lu, Kai Chen, Xiaohuai Le","submitted_at":"2021-07-12T13:50:27Z","abstract_excerpt":"The dual-path RNN (DPRNN) was proposed to more effectively model extremely long sequences for speech separation in the time domain. By splitting long sequences to smaller chunks and applying intra-chunk and inter-chunk RNNs, the DPRNN reached promising performance in speech separation with a limited model size. In this paper, we combine the DPRNN module with Convolution Recurrent Network (CRN) and design a model called Dual-Path Convolution Recurrent Network (DPCRN) for speech enhancement in the time-frequency domain. We replace the RNNs in the CRN with DPRNN modules, where the intra-chunk RNN"},"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":"2107.05429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-07-12T13:50:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5ec350a42c69ee3c11e9e0b39b422914935d2c5c94a9d8e31fc697ea13c55046","abstract_canon_sha256":"f3c7b7567e0c643c4260dd29c2e61c57101add3c98a39e0137aafd2ccd230ed6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:02.721222Z","signature_b64":"tqFq+a7ex0lsxDGHq9ThXIk0VUi+5koeMqOYKOH6zEyo6U/pK+OFA/TMFi7CWS7f+1A1ZtcFDJdZJeHvy9ILBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"765e3754252371b13ce6c2da0a36eb63090a9addbe4b6d01eb223c1b9697cdc0","last_reissued_at":"2026-07-05T02:57:02.720876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:02.720876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongsheng Chen, Jing Lu, Kai Chen, Xiaohuai Le","submitted_at":"2021-07-12T13:50:27Z","abstract_excerpt":"The dual-path RNN (DPRNN) was proposed to more effectively model extremely long sequences for speech separation in the time domain. By splitting long sequences to smaller chunks and applying intra-chunk and inter-chunk RNNs, the DPRNN reached promising performance in speech separation with a limited model size. In this paper, we combine the DPRNN module with Convolution Recurrent Network (CRN) and design a model called Dual-Path Convolution Recurrent Network (DPCRN) for speech enhancement in the time-frequency domain. We replace the RNNs in the CRN with DPRNN modules, where the intra-chunk RNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05429","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/2107.05429/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":"2107.05429","created_at":"2026-07-05T02:57:02.720934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.05429v1","created_at":"2026-07-05T02:57:02.720934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05429","created_at":"2026-07-05T02:57:02.720934+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZPDOVBFENY3","created_at":"2026-07-05T02:57:02.720934+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZPDOVBFENY3CPHG","created_at":"2026-07-05T02:57:02.720934+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZPDOVBF","created_at":"2026-07-05T02:57:02.720934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07341","citing_title":"Affine Modulation-based Audiogram Fusion Network for Joint Noise Reduction and Hearing Loss Compensation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM","json":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM.json","graph_json":"https://pith.science/api/pith-number/OZPDOVBFENY3CPHGYLNAUNXLMM/graph.json","events_json":"https://pith.science/api/pith-number/OZPDOVBFENY3CPHGYLNAUNXLMM/events.json","paper":"https://pith.science/paper/OZPDOVBF"},"agent_actions":{"view_html":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM","download_json":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM.json","view_paper":"https://pith.science/paper/OZPDOVBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.05429&json=true","fetch_graph":"https://pith.science/api/pith-number/OZPDOVBFENY3CPHGYLNAUNXLMM/graph.json","fetch_events":"https://pith.science/api/pith-number/OZPDOVBFENY3CPHGYLNAUNXLMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM/action/storage_attestation","attest_author":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM/action/author_attestation","sign_citation":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM/action/citation_signature","submit_replication":"https://pith.science/pith/OZPDOVBFENY3CPHGYLNAUNXLMM/action/replication_record"}},"created_at":"2026-07-05T02:57:02.720934+00:00","updated_at":"2026-07-05T02:57:02.720934+00:00"}