{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5JWYWL5YZWYGC4GCUXFRFMZUL2","short_pith_number":"pith:5JWYWL5Y","schema_version":"1.0","canonical_sha256":"ea6d8b2fb8cdb06170c2a5cb12b3345e9d50db9169f14c5571ec64af76b921e0","source":{"kind":"arxiv","id":"2107.13530","version":2},"attestation_state":"computed","paper":{"title":"An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bethan Thomas, Salah Karout, Samuel Kessler","submitted_at":"2021-07-26T10:39:03Z","abstract_excerpt":"We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on small annotated datasets is a promising direction to build speech recognition systems. SSL models generally perform SSL on raw audio in a pre-training phase and then fine-tune on a small fraction of annotated data. Such models have produced state of the art results for ASR. However, these models are very expensive to pre-train. We use an existing wav2vec 2.0"},"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":"2107.13530","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-07-26T10:39:03Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"41b5e34f27e12ed21b895768704f0203b113718609b4b8d4e2cd826d86f2c841","abstract_canon_sha256":"9c0bf11d5eaed10b5cdc1cdae3c9fdb121dbc5980bf19d66f11baf43a97e386e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:22.459969Z","signature_b64":"0FejD9D+HAXhyIi/YUE6X1hN5564wRI4PtYXRhGT6j9UqIXa4VL4tbBi640I1ZyYmiTLHSPE36wvBrLHnUcGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea6d8b2fb8cdb06170c2a5cb12b3345e9d50db9169f14c5571ec64af76b921e0","last_reissued_at":"2026-07-05T03:54:22.459454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:22.459454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bethan Thomas, Salah Karout, Samuel Kessler","submitted_at":"2021-07-26T10:39:03Z","abstract_excerpt":"We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on small annotated datasets is a promising direction to build speech recognition systems. SSL models generally perform SSL on raw audio in a pre-training phase and then fine-tune on a small fraction of annotated data. Such models have produced state of the art results for ASR. However, these models are very expensive to pre-train. We use an existing wav2vec 2.0"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13530","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/2107.13530/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":"2107.13530","created_at":"2026-07-05T03:54:22.459511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13530v2","created_at":"2026-07-05T03:54:22.459511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13530","created_at":"2026-07-05T03:54:22.459511+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JWYWL5YZWYG","created_at":"2026-07-05T03:54:22.459511+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JWYWL5YZWYGC4GC","created_at":"2026-07-05T03:54:22.459511+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JWYWL5Y","created_at":"2026-07-05T03:54:22.459511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18368","citing_title":"AMPS: ASR with Multimodal Paraphrase Supervision","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2","json":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2.json","graph_json":"https://pith.science/api/pith-number/5JWYWL5YZWYGC4GCUXFRFMZUL2/graph.json","events_json":"https://pith.science/api/pith-number/5JWYWL5YZWYGC4GCUXFRFMZUL2/events.json","paper":"https://pith.science/paper/5JWYWL5Y"},"agent_actions":{"view_html":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2","download_json":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2.json","view_paper":"https://pith.science/paper/5JWYWL5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13530&json=true","fetch_graph":"https://pith.science/api/pith-number/5JWYWL5YZWYGC4GCUXFRFMZUL2/graph.json","fetch_events":"https://pith.science/api/pith-number/5JWYWL5YZWYGC4GCUXFRFMZUL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2/action/storage_attestation","attest_author":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2/action/author_attestation","sign_citation":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2/action/citation_signature","submit_replication":"https://pith.science/pith/5JWYWL5YZWYGC4GCUXFRFMZUL2/action/replication_record"}},"created_at":"2026-07-05T03:54:22.459511+00:00","updated_at":"2026-07-05T03:54:22.459511+00:00"}