{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IIZZYYMOTEKVWNJW4A45ID2Z3K","short_pith_number":"pith:IIZZYYMO","schema_version":"1.0","canonical_sha256":"42339c618e99155b3536e039d40f59dab3d29dcc46c7b768507b36815deadde6","source":{"kind":"arxiv","id":"2205.10643","version":3},"attestation_state":"computed","paper":{"title":"Self-Supervised Speech Representation Learning: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Christian Igel, Hung-yi Lee, Jakob D. Havtorn, Joakim Edin, Karen Livescu, Katrin Kirchhoff, Lars Maal{\\o}e, Lasse Borgholt, Shang-Wen Li, Shinji Watanabe, Tara N. Sainath","submitted_at":"2022-05-21T16:52:57Z","abstract_excerpt":"Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels "},"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":"2205.10643","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T16:52:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d38d92dfaad2da641880e13003e37a8ef23f3ff7872626e68a66dfef2ce1c58d","abstract_canon_sha256":"d5fde2ae213f4a4f1cf9c2a8e51ef6b0bfab7115cd06dcb86809aa0e65c60b74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:31.875253Z","signature_b64":"fOoH03QAJDhMfFo1UBejKKzGrWJbHOtBoqg8hoBerzBpcemZNpb+CsuCVi/13gN0sDCIZ+sStBgqvKE55mo7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42339c618e99155b3536e039d40f59dab3d29dcc46c7b768507b36815deadde6","last_reissued_at":"2026-07-05T05:18:31.874835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:31.874835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Speech Representation Learning: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Christian Igel, Hung-yi Lee, Jakob D. Havtorn, Joakim Edin, Karen Livescu, Katrin Kirchhoff, Lars Maal{\\o}e, Lasse Borgholt, Shang-Wen Li, Shinji Watanabe, Tara N. Sainath","submitted_at":"2022-05-21T16:52:57Z","abstract_excerpt":"Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10643","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/2205.10643/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":"2205.10643","created_at":"2026-07-05T05:18:31.874891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10643v3","created_at":"2026-07-05T05:18:31.874891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10643","created_at":"2026-07-05T05:18:31.874891+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIZZYYMOTEKV","created_at":"2026-07-05T05:18:31.874891+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIZZYYMOTEKVWNJW","created_at":"2026-07-05T05:18:31.874891+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIZZYYMO","created_at":"2026-07-05T05:18:31.874891+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/IIZZYYMOTEKVWNJW4A45ID2Z3K","json":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K.json","graph_json":"https://pith.science/api/pith-number/IIZZYYMOTEKVWNJW4A45ID2Z3K/graph.json","events_json":"https://pith.science/api/pith-number/IIZZYYMOTEKVWNJW4A45ID2Z3K/events.json","paper":"https://pith.science/paper/IIZZYYMO"},"agent_actions":{"view_html":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K","download_json":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K.json","view_paper":"https://pith.science/paper/IIZZYYMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10643&json=true","fetch_graph":"https://pith.science/api/pith-number/IIZZYYMOTEKVWNJW4A45ID2Z3K/graph.json","fetch_events":"https://pith.science/api/pith-number/IIZZYYMOTEKVWNJW4A45ID2Z3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K/action/storage_attestation","attest_author":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K/action/author_attestation","sign_citation":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K/action/citation_signature","submit_replication":"https://pith.science/pith/IIZZYYMOTEKVWNJW4A45ID2Z3K/action/replication_record"}},"created_at":"2026-07-05T05:18:31.874891+00:00","updated_at":"2026-07-05T05:18:31.874891+00:00"}