{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GSTQWTNYOYFRWGA544KDHSYX3D","short_pith_number":"pith:GSTQWTNY","schema_version":"1.0","canonical_sha256":"34a70b4db8760b1b181de71433cb17d8d8f826d0f795bffcbf2198936d587d47","source":{"kind":"arxiv","id":"2008.00264","version":4},"attestation_state":"computed","paper":{"title":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bihong Zhang, Jian Wu, Lei Xie, Mengtao Xing, Shimin Zhang, Shubo Lv, Yanxin Hu, Yihui Fu, Yun Liu","submitted_at":"2020-08-01T13:42:29Z","abstract_excerpt":"Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution neural network (CNN) or recurrent neural network (RNN). Some recent studies use complex-valued spectrogram as a training target but train in a real-valued network, predicting the magnitude and phase component or real and imaginary part, respectively. Particularly, convolution recurrent network (CRN) integrates a convolutional encoder-decoder (CED) structure "},"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":"2008.00264","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-01T13:42:29Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"cce870d76a46c96d60a7ad096fa73ffbc33fae1614391eb8ef76eb526d544abd","abstract_canon_sha256":"527a73deac65252e3b7d87e2f6902920a4df349748815c63fb683074ce531591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:24.787212Z","signature_b64":"VPOYcO1G2WWir/h0B/SnesUWfSgQmCIFDvbDoLFU8um/dhgUMwy8Xp622ciLz1nAEmegb7qNAfYcmRujxi7FAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34a70b4db8760b1b181de71433cb17d8d8f826d0f795bffcbf2198936d587d47","last_reissued_at":"2026-07-05T01:37:24.786809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:24.786809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bihong Zhang, Jian Wu, Lei Xie, Mengtao Xing, Shimin Zhang, Shubo Lv, Yanxin Hu, Yihui Fu, Yun Liu","submitted_at":"2020-08-01T13:42:29Z","abstract_excerpt":"Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution neural network (CNN) or recurrent neural network (RNN). Some recent studies use complex-valued spectrogram as a training target but train in a real-valued network, predicting the magnitude and phase component or real and imaginary part, respectively. Particularly, convolution recurrent network (CRN) integrates a convolutional encoder-decoder (CED) structure "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00264","kind":"arxiv","version":4},"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/2008.00264/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":"2008.00264","created_at":"2026-07-05T01:37:24.786869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.00264v4","created_at":"2026-07-05T01:37:24.786869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00264","created_at":"2026-07-05T01:37:24.786869+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSTQWTNYOYFR","created_at":"2026-07-05T01:37:24.786869+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSTQWTNYOYFRWGA5","created_at":"2026-07-05T01:37:24.786869+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSTQWTNY","created_at":"2026-07-05T01:37:24.786869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12534","citing_title":"BioSEN: A Bio-acoustic Signal Enhancement Network for Animal Vocalizations","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12534","citing_title":"BioSEN: A Bio-acoustic Signal Enhancement Network for Animal Vocalizations","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19221","citing_title":"UAF: A Unified Audio Front-end LLM for Full-Duplex Speech Interaction","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D","json":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D.json","graph_json":"https://pith.science/api/pith-number/GSTQWTNYOYFRWGA544KDHSYX3D/graph.json","events_json":"https://pith.science/api/pith-number/GSTQWTNYOYFRWGA544KDHSYX3D/events.json","paper":"https://pith.science/paper/GSTQWTNY"},"agent_actions":{"view_html":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D","download_json":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D.json","view_paper":"https://pith.science/paper/GSTQWTNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.00264&json=true","fetch_graph":"https://pith.science/api/pith-number/GSTQWTNYOYFRWGA544KDHSYX3D/graph.json","fetch_events":"https://pith.science/api/pith-number/GSTQWTNYOYFRWGA544KDHSYX3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D/action/storage_attestation","attest_author":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D/action/author_attestation","sign_citation":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D/action/citation_signature","submit_replication":"https://pith.science/pith/GSTQWTNYOYFRWGA544KDHSYX3D/action/replication_record"}},"created_at":"2026-07-05T01:37:24.786869+00:00","updated_at":"2026-07-05T01:37:24.786869+00:00"}