{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HCGTJJMD7UD3O7RRZSVEU7M7GL","short_pith_number":"pith:HCGTJJMD","schema_version":"1.0","canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","source":{"kind":"arxiv","id":"2105.11084","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Alexis Conneau, Michael Auli, Wei-Ning Hsu","submitted_at":"2021-05-24T04:10:47Z","abstract_excerpt":"Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsu"},"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":"2105.11084","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T04:10:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"75d5a8f65b37e79eb4654ba2c2dfe7c0c90abc283a81e299884a345c191047b1","abstract_canon_sha256":"bf1148fa49a7bcbca81d10dad93fcd6625dc2eeeca4f50f41dbe0ba3b583a9b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:31.675024Z","signature_b64":"nt/AE7LW+P4RItOrESGdx3QrnBE9zaJUXalM47dcW461C1XarBviLgVdDcpvQpVrpODm8LnOf9Uv2lVAc90nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","last_reissued_at":"2026-07-05T04:19:31.674622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:31.674622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Alexis Conneau, Michael Auli, Wei-Ning Hsu","submitted_at":"2021-05-24T04:10:47Z","abstract_excerpt":"Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11084","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/2105.11084/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":"2105.11084","created_at":"2026-07-05T04:19:31.674679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11084v3","created_at":"2026-07-05T04:19:31.674679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11084","created_at":"2026-07-05T04:19:31.674679+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCGTJJMD7UD3","created_at":"2026-07-05T04:19:31.674679+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCGTJJMD7UD3O7RR","created_at":"2026-07-05T04:19:31.674679+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCGTJJMD","created_at":"2026-07-05T04:19:31.674679+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/HCGTJJMD7UD3O7RRZSVEU7M7GL","json":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL.json","graph_json":"https://pith.science/api/pith-number/HCGTJJMD7UD3O7RRZSVEU7M7GL/graph.json","events_json":"https://pith.science/api/pith-number/HCGTJJMD7UD3O7RRZSVEU7M7GL/events.json","paper":"https://pith.science/paper/HCGTJJMD"},"agent_actions":{"view_html":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL","download_json":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL.json","view_paper":"https://pith.science/paper/HCGTJJMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11084&json=true","fetch_graph":"https://pith.science/api/pith-number/HCGTJJMD7UD3O7RRZSVEU7M7GL/graph.json","fetch_events":"https://pith.science/api/pith-number/HCGTJJMD7UD3O7RRZSVEU7M7GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/action/storage_attestation","attest_author":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/action/author_attestation","sign_citation":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/action/citation_signature","submit_replication":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/action/replication_record"}},"created_at":"2026-07-05T04:19:31.674679+00:00","updated_at":"2026-07-05T04:19:31.674679+00:00"}