{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3D2LNB7VMY33XI3FFUDDDWB5AY","short_pith_number":"pith:3D2LNB7V","schema_version":"1.0","canonical_sha256":"d8f4b687f56637bba3652d0631d83d062837be8923607cde3c64e2f1b0d96396","source":{"kind":"arxiv","id":"2202.01855","version":2},"attestation_state":"computed","paper":{"title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chung-Cheng Chiu, James Qin, Jiahui Yu, Yonghui Wu, Yu Zhang","submitted_at":"2022-02-03T21:29:04Z","abstract_excerpt":"We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In particular the quantizer projects speech inputs with a randomly initialized matrix, and does a nearest-neighbor lookup in a randomly-initialized codebook. Neither the matrix nor the codebook is updated during self-supervised learning. Since the random-projection quantizer is not trained and is separated from the speech recognition model, the design makes the a"},"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":"2202.01855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-03T21:29:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5141ac34c95ec5c228d5ae4c341105b76b31f40b2e59bb264901e0946fdc19ef","abstract_canon_sha256":"6b449e34e0029a6e8cb474205307e5b8164b9bb03bf3bd4ee5c49007d7eb1ca3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:09.724733Z","signature_b64":"6dl5iGMPLS30MkvmzM/8J5g4tDk2MJlM3CmoD09isZZL8esoJAa/rohA+oYjl9hQds2vE1AKykfzXfxpzprxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8f4b687f56637bba3652d0631d83d062837be8923607cde3c64e2f1b0d96396","last_reissued_at":"2026-07-05T04:36:09.724275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:09.724275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chung-Cheng Chiu, James Qin, Jiahui Yu, Yonghui Wu, Yu Zhang","submitted_at":"2022-02-03T21:29:04Z","abstract_excerpt":"We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In particular the quantizer projects speech inputs with a randomly initialized matrix, and does a nearest-neighbor lookup in a randomly-initialized codebook. Neither the matrix nor the codebook is updated during self-supervised learning. Since the random-projection quantizer is not trained and is separated from the speech recognition model, the design makes the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01855","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/2202.01855/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":"2202.01855","created_at":"2026-07-05T04:36:09.724343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01855v2","created_at":"2026-07-05T04:36:09.724343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01855","created_at":"2026-07-05T04:36:09.724343+00:00"},{"alias_kind":"pith_short_12","alias_value":"3D2LNB7VMY33","created_at":"2026-07-05T04:36:09.724343+00:00"},{"alias_kind":"pith_short_16","alias_value":"3D2LNB7VMY33XI3F","created_at":"2026-07-05T04:36:09.724343+00:00"},{"alias_kind":"pith_short_8","alias_value":"3D2LNB7V","created_at":"2026-07-05T04:36:09.724343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19774","citing_title":"DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY","json":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY.json","graph_json":"https://pith.science/api/pith-number/3D2LNB7VMY33XI3FFUDDDWB5AY/graph.json","events_json":"https://pith.science/api/pith-number/3D2LNB7VMY33XI3FFUDDDWB5AY/events.json","paper":"https://pith.science/paper/3D2LNB7V"},"agent_actions":{"view_html":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY","download_json":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY.json","view_paper":"https://pith.science/paper/3D2LNB7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01855&json=true","fetch_graph":"https://pith.science/api/pith-number/3D2LNB7VMY33XI3FFUDDDWB5AY/graph.json","fetch_events":"https://pith.science/api/pith-number/3D2LNB7VMY33XI3FFUDDDWB5AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY/action/storage_attestation","attest_author":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY/action/author_attestation","sign_citation":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY/action/citation_signature","submit_replication":"https://pith.science/pith/3D2LNB7VMY33XI3FFUDDDWB5AY/action/replication_record"}},"created_at":"2026-07-05T04:36:09.724343+00:00","updated_at":"2026-07-05T04:36:09.724343+00:00"}