{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BG4DC76ICBWGOY7VQXT6SETZX2","short_pith_number":"pith:BG4DC76I","schema_version":"1.0","canonical_sha256":"09b8317fc8106c6763f585e7e91279be8be1bb254496f3440393645a93da3886","source":{"kind":"arxiv","id":"2302.14597","version":1},"attestation_state":"computed","paper":{"title":"deHuBERT: Disentangling Noise in a Self-supervised Model for Robust Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Eng Siong Chng, Jia Qi Yip, Jinjie Ni, Ruixi Zhang, Yukun Ma, Zhao Yang","submitted_at":"2023-02-28T14:33:41Z","abstract_excerpt":"Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a single source, which tends to do poorly when noise is present during testing. Nonetheless, it is crucial to overcome the adverse influence of noise for real-world applications. In this work, we propose a novel training framework, called deHuBERT, for noise reduction encoding inspired by H. Barlow's redundancy-reduction principle. The new framework improves the "},"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":"2302.14597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-02-28T14:33:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"63f6450f66008d27583a84a881d73f55379c20970a507fc6226ad64ad179eb19","abstract_canon_sha256":"cb8539d81319ad855c299bf9646c60de609e5fc55aa5312f55f1662f85cee267"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:46.984288Z","signature_b64":"z0VykH4apcRDR/mjkweBYINtI9RWEHqPQOiIiCWrUCBVbGuAm4CG4G/bF2o4T5+o5MIx086vUv5LocNbtm8hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09b8317fc8106c6763f585e7e91279be8be1bb254496f3440393645a93da3886","last_reissued_at":"2026-07-05T05:46:46.983859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:46.983859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"deHuBERT: Disentangling Noise in a Self-supervised Model for Robust Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Eng Siong Chng, Jia Qi Yip, Jinjie Ni, Ruixi Zhang, Yukun Ma, Zhao Yang","submitted_at":"2023-02-28T14:33:41Z","abstract_excerpt":"Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a single source, which tends to do poorly when noise is present during testing. Nonetheless, it is crucial to overcome the adverse influence of noise for real-world applications. In this work, we propose a novel training framework, called deHuBERT, for noise reduction encoding inspired by H. Barlow's redundancy-reduction principle. The new framework improves the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14597","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/2302.14597/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":"2302.14597","created_at":"2026-07-05T05:46:46.983916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14597v1","created_at":"2026-07-05T05:46:46.983916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14597","created_at":"2026-07-05T05:46:46.983916+00:00"},{"alias_kind":"pith_short_12","alias_value":"BG4DC76ICBWG","created_at":"2026-07-05T05:46:46.983916+00:00"},{"alias_kind":"pith_short_16","alias_value":"BG4DC76ICBWGOY7V","created_at":"2026-07-05T05:46:46.983916+00:00"},{"alias_kind":"pith_short_8","alias_value":"BG4DC76I","created_at":"2026-07-05T05:46:46.983916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2","json":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2.json","graph_json":"https://pith.science/api/pith-number/BG4DC76ICBWGOY7VQXT6SETZX2/graph.json","events_json":"https://pith.science/api/pith-number/BG4DC76ICBWGOY7VQXT6SETZX2/events.json","paper":"https://pith.science/paper/BG4DC76I"},"agent_actions":{"view_html":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2","download_json":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2.json","view_paper":"https://pith.science/paper/BG4DC76I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14597&json=true","fetch_graph":"https://pith.science/api/pith-number/BG4DC76ICBWGOY7VQXT6SETZX2/graph.json","fetch_events":"https://pith.science/api/pith-number/BG4DC76ICBWGOY7VQXT6SETZX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2/action/storage_attestation","attest_author":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2/action/author_attestation","sign_citation":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2/action/citation_signature","submit_replication":"https://pith.science/pith/BG4DC76ICBWGOY7VQXT6SETZX2/action/replication_record"}},"created_at":"2026-07-05T05:46:46.983916+00:00","updated_at":"2026-07-05T05:46:46.983916+00:00"}