{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZJFCIIXKI3QDNF3HMPLZSHVKE4","short_pith_number":"pith:ZJFCIIXK","schema_version":"1.0","canonical_sha256":"ca4a2422ea46e036976763d7991eaa2709bd5dd045fb9c385f969fac90d9a61a","source":{"kind":"arxiv","id":"2012.09408","version":2},"attestation_state":"computed","paper":{"title":"Interactive Speech and Noise Modeling for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Chengyu Zheng, Sriram Srinivasan, Xiulian Peng, Yan Lu, Yuan Zhang","submitted_at":"2020-12-17T06:18:31Z","abstract_excerpt":"Speech enhancement is challenging because of the diversity of background noise types. Most of the existing methods are focused on modelling the speech rather than the noise. In this paper, we propose a novel idea to model speech and noise simultaneously in a two-branch convolutional neural network, namely SN-Net. In SN-Net, the two branches predict speech and noise, respectively. Instead of information fusion only at the final output layer, interaction modules are introduced at several intermediate feature domains between the two branches to benefit each other. Such an interaction can leverage"},"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":"2012.09408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-12-17T06:18:31Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"6111fa8ed407d72024ddd7866774abee6633bdfd22245f94bf255b4bf69af014","abstract_canon_sha256":"cc15fc99c03302186d561bd9b44c4b8153d92d474379345f8906a01a4a0a99c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:02.575574Z","signature_b64":"SoFsygIdT2o/gyEtYF92HblWJp4Z1mTLuNZzhVO8U7QyvmlYhvs1Uydyc7ceGY14/7dxJFpvIe7y1lyg7g+bBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4a2422ea46e036976763d7991eaa2709bd5dd045fb9c385f969fac90d9a61a","last_reissued_at":"2026-07-05T02:32:02.575085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:02.575085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Speech and Noise Modeling for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Chengyu Zheng, Sriram Srinivasan, Xiulian Peng, Yan Lu, Yuan Zhang","submitted_at":"2020-12-17T06:18:31Z","abstract_excerpt":"Speech enhancement is challenging because of the diversity of background noise types. Most of the existing methods are focused on modelling the speech rather than the noise. In this paper, we propose a novel idea to model speech and noise simultaneously in a two-branch convolutional neural network, namely SN-Net. In SN-Net, the two branches predict speech and noise, respectively. Instead of information fusion only at the final output layer, interaction modules are introduced at several intermediate feature domains between the two branches to benefit each other. Such an interaction can leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09408","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/2012.09408/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":"2012.09408","created_at":"2026-07-05T02:32:02.575143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.09408v2","created_at":"2026-07-05T02:32:02.575143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09408","created_at":"2026-07-05T02:32:02.575143+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJFCIIXKI3QD","created_at":"2026-07-05T02:32:02.575143+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJFCIIXKI3QDNF3H","created_at":"2026-07-05T02:32:02.575143+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJFCIIXK","created_at":"2026-07-05T02:32:02.575143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06697","citing_title":"Exploring Length Generalization For Transformer-based Speech Enhancement","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4","json":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4.json","graph_json":"https://pith.science/api/pith-number/ZJFCIIXKI3QDNF3HMPLZSHVKE4/graph.json","events_json":"https://pith.science/api/pith-number/ZJFCIIXKI3QDNF3HMPLZSHVKE4/events.json","paper":"https://pith.science/paper/ZJFCIIXK"},"agent_actions":{"view_html":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4","download_json":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4.json","view_paper":"https://pith.science/paper/ZJFCIIXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.09408&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJFCIIXKI3QDNF3HMPLZSHVKE4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJFCIIXKI3QDNF3HMPLZSHVKE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4/action/storage_attestation","attest_author":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4/action/author_attestation","sign_citation":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4/action/citation_signature","submit_replication":"https://pith.science/pith/ZJFCIIXKI3QDNF3HMPLZSHVKE4/action/replication_record"}},"created_at":"2026-07-05T02:32:02.575143+00:00","updated_at":"2026-07-05T02:32:02.575143+00:00"}