{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RWHWDHWYBPOIDJSQXC6223XJG2","short_pith_number":"pith:RWHWDHWY","schema_version":"1.0","canonical_sha256":"8d8f619ed80bdc81a650b8bdad6ee93682c3dda891bdc4d497d72e8cec9101d8","source":{"kind":"arxiv","id":"2201.10207","version":3},"attestation_state":"computed","paper":{"title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Qun Liu, Wenyong Huang, Xin Jiang, Yu Ting Yeung, Zhenhe Zhang","submitted_at":"2022-01-25T09:53:36Z","abstract_excerpt":"We introduce a new approach for speech pre-training named SPIRAL which works by learning denoising representation of perturbed data in a teacher-student framework. Specifically, given a speech utterance, we first feed the utterance to a teacher network to obtain corresponding representation. Then the same utterance is perturbed and fed to a student network. The student network is trained to output representation resembling that of the teacher. At the same time, the teacher network is updated as moving average of student's weights over training steps. In order to prevent representation collapse"},"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":"2201.10207","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-01-25T09:53:36Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"af0632a4eb268e039f86428868ac16a1dcac8e3309b10b3751bf3e5818e01497","abstract_canon_sha256":"d54421e2b8d1f2bd754132d74b074c2e4bb51584a51657a19244749fd8c2f0da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:22.721242Z","signature_b64":"DE1D1XddbbzRvq1W5eSy8H/9zhRyQ5/oU4Ku189MKiY8jXMbw1mh+Vm/EqBkjbdZTDA+zfUDmVMLo6KECYnkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d8f619ed80bdc81a650b8bdad6ee93682c3dda891bdc4d497d72e8cec9101d8","last_reissued_at":"2026-07-05T04:02:22.720755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:22.720755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Qun Liu, Wenyong Huang, Xin Jiang, Yu Ting Yeung, Zhenhe Zhang","submitted_at":"2022-01-25T09:53:36Z","abstract_excerpt":"We introduce a new approach for speech pre-training named SPIRAL which works by learning denoising representation of perturbed data in a teacher-student framework. Specifically, given a speech utterance, we first feed the utterance to a teacher network to obtain corresponding representation. Then the same utterance is perturbed and fed to a student network. The student network is trained to output representation resembling that of the teacher. At the same time, the teacher network is updated as moving average of student's weights over training steps. In order to prevent representation collapse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10207","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/2201.10207/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":"2201.10207","created_at":"2026-07-05T04:02:22.720815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10207v3","created_at":"2026-07-05T04:02:22.720815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10207","created_at":"2026-07-05T04:02:22.720815+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWHWDHWYBPOI","created_at":"2026-07-05T04:02:22.720815+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWHWDHWYBPOIDJSQ","created_at":"2026-07-05T04:02:22.720815+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWHWDHWY","created_at":"2026-07-05T04:02:22.720815+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/RWHWDHWYBPOIDJSQXC6223XJG2","json":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2.json","graph_json":"https://pith.science/api/pith-number/RWHWDHWYBPOIDJSQXC6223XJG2/graph.json","events_json":"https://pith.science/api/pith-number/RWHWDHWYBPOIDJSQXC6223XJG2/events.json","paper":"https://pith.science/paper/RWHWDHWY"},"agent_actions":{"view_html":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2","download_json":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2.json","view_paper":"https://pith.science/paper/RWHWDHWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10207&json=true","fetch_graph":"https://pith.science/api/pith-number/RWHWDHWYBPOIDJSQXC6223XJG2/graph.json","fetch_events":"https://pith.science/api/pith-number/RWHWDHWYBPOIDJSQXC6223XJG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2/action/storage_attestation","attest_author":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2/action/author_attestation","sign_citation":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2/action/citation_signature","submit_replication":"https://pith.science/pith/RWHWDHWYBPOIDJSQXC6223XJG2/action/replication_record"}},"created_at":"2026-07-05T04:02:22.720815+00:00","updated_at":"2026-07-05T04:02:22.720815+00:00"}