{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PY5Y2Y2ML2Y2DUPOAOONPRN3QW","short_pith_number":"pith:PY5Y2Y2M","schema_version":"1.0","canonical_sha256":"7e3b8d634c5eb1a1d1ee039cd7c5bb85913d573d9d3e29174d83341f48b942ba","source":{"kind":"arxiv","id":"2305.10761","version":3},"attestation_state":"computed","paper":{"title":"Noise-Aware Speech Separation with Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Chen, Eng Siong Chng, Hsin-Hung Chen, Xiang Liu, Yuchen Hu, Zizheng Zhang","submitted_at":"2023-05-18T07:06:15Z","abstract_excerpt":"Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background noise to each speaker. In this paper, we propose a noise-aware SS (NASS) method, which aims to improve the speech quality for separated signals under noisy conditions. Specifically, NASS views background noise as an additional output and predicts it along with other speakers in a mask-based manner. To effectively denoise, we introduce patch-wise contrastive "},"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":"2305.10761","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-18T07:06:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4d08445bd6a43909aa5431463b0bce9075e95f200df2a0562dd67f7d524190ed","abstract_canon_sha256":"b7a87ab52b341fd0d67336ed2ccae0f9ad154a1d840f868a92ddd4a025fa9362"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:49.151057Z","signature_b64":"NysDDrpxPBMuHAN2ifu3Lx5QTghnrtIpT3Rp/vSIwnn8L7PkuEFkyqag8fuoGiwgZ/r0U9qo+T9xfYJL9QgZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e3b8d634c5eb1a1d1ee039cd7c5bb85913d573d9d3e29174d83341f48b942ba","last_reissued_at":"2026-07-05T07:30:49.150631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:49.150631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-Aware Speech Separation with Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Chen, Eng Siong Chng, Hsin-Hung Chen, Xiang Liu, Yuchen Hu, Zizheng Zhang","submitted_at":"2023-05-18T07:06:15Z","abstract_excerpt":"Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background noise to each speaker. In this paper, we propose a noise-aware SS (NASS) method, which aims to improve the speech quality for separated signals under noisy conditions. Specifically, NASS views background noise as an additional output and predicts it along with other speakers in a mask-based manner. To effectively denoise, we introduce patch-wise contrastive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10761","kind":"arxiv","version":3},"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/2305.10761/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":"2305.10761","created_at":"2026-07-05T07:30:49.150690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10761v3","created_at":"2026-07-05T07:30:49.150690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10761","created_at":"2026-07-05T07:30:49.150690+00:00"},{"alias_kind":"pith_short_12","alias_value":"PY5Y2Y2ML2Y2","created_at":"2026-07-05T07:30:49.150690+00:00"},{"alias_kind":"pith_short_16","alias_value":"PY5Y2Y2ML2Y2DUPO","created_at":"2026-07-05T07:30:49.150690+00:00"},{"alias_kind":"pith_short_8","alias_value":"PY5Y2Y2M","created_at":"2026-07-05T07:30:49.150690+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/PY5Y2Y2ML2Y2DUPOAOONPRN3QW","json":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW.json","graph_json":"https://pith.science/api/pith-number/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/graph.json","events_json":"https://pith.science/api/pith-number/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/events.json","paper":"https://pith.science/paper/PY5Y2Y2M"},"agent_actions":{"view_html":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW","download_json":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW.json","view_paper":"https://pith.science/paper/PY5Y2Y2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10761&json=true","fetch_graph":"https://pith.science/api/pith-number/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/graph.json","fetch_events":"https://pith.science/api/pith-number/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/action/storage_attestation","attest_author":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/action/author_attestation","sign_citation":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/action/citation_signature","submit_replication":"https://pith.science/pith/PY5Y2Y2ML2Y2DUPOAOONPRN3QW/action/replication_record"}},"created_at":"2026-07-05T07:30:49.150690+00:00","updated_at":"2026-07-05T07:30:49.150690+00:00"}