{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2LO4QGGU5YYUP7RN73KA4T75S5","short_pith_number":"pith:2LO4QGGU","schema_version":"1.0","canonical_sha256":"d2ddc818d4ee3147fe2dfed40e4ffd97511fc85e5f04ec3c934d5b6da8da0585","source":{"kind":"arxiv","id":"2408.13106","version":6},"attestation_state":"computed","paper":{"title":"NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Nithin Rao Koluguri, Taejin Park, Weiqing Wang","submitted_at":"2024-08-23T14:32:18Z","abstract_excerpt":"Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally expensive. In this paper, we propose a simplified and more efficient self-supervised learning framework termed as NeMo Encoder for Speech Tasks (NEST). Specifically, we adopt the FastConformer architecture with 8x sub-sampling rate, which is faster than Transformer or Conformer architectures. Instead of clustering-based quantization, we use fixed random projection f"},"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":"2408.13106","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-23T14:32:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cf02bca0116fdf4833a8206d314d99ceb50099148262ea3c6f4bf0dcdb2fd75e","abstract_canon_sha256":"47a2a5b62ba2fdfc6bdaa161313ef49c6749b96a07bc26bea6009762ac70c2b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:24.149485Z","signature_b64":"12yxEKKSey4ou0PUdhdfuDoa7sTeALIks2vuC9IOVsIOOeRZ75e7MPG3RztIegw0bS2GBI/FDMl3HeGQmyP/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2ddc818d4ee3147fe2dfed40e4ffd97511fc85e5f04ec3c934d5b6da8da0585","last_reissued_at":"2026-07-05T10:02:24.149093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:24.149093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Nithin Rao Koluguri, Taejin Park, Weiqing Wang","submitted_at":"2024-08-23T14:32:18Z","abstract_excerpt":"Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally expensive. In this paper, we propose a simplified and more efficient self-supervised learning framework termed as NeMo Encoder for Speech Tasks (NEST). Specifically, we adopt the FastConformer architecture with 8x sub-sampling rate, which is faster than Transformer or Conformer architectures. Instead of clustering-based quantization, we use fixed random projection f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13106","kind":"arxiv","version":6},"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/2408.13106/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":"2408.13106","created_at":"2026-07-05T10:02:24.149149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13106v6","created_at":"2026-07-05T10:02:24.149149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13106","created_at":"2026-07-05T10:02:24.149149+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LO4QGGU5YYU","created_at":"2026-07-05T10:02:24.149149+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LO4QGGU5YYUP7RN","created_at":"2026-07-05T10:02:24.149149+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LO4QGGU","created_at":"2026-07-05T10:02:24.149149+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/2LO4QGGU5YYUP7RN73KA4T75S5","json":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5.json","graph_json":"https://pith.science/api/pith-number/2LO4QGGU5YYUP7RN73KA4T75S5/graph.json","events_json":"https://pith.science/api/pith-number/2LO4QGGU5YYUP7RN73KA4T75S5/events.json","paper":"https://pith.science/paper/2LO4QGGU"},"agent_actions":{"view_html":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5","download_json":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5.json","view_paper":"https://pith.science/paper/2LO4QGGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13106&json=true","fetch_graph":"https://pith.science/api/pith-number/2LO4QGGU5YYUP7RN73KA4T75S5/graph.json","fetch_events":"https://pith.science/api/pith-number/2LO4QGGU5YYUP7RN73KA4T75S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5/action/storage_attestation","attest_author":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5/action/author_attestation","sign_citation":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5/action/citation_signature","submit_replication":"https://pith.science/pith/2LO4QGGU5YYUP7RN73KA4T75S5/action/replication_record"}},"created_at":"2026-07-05T10:02:24.149149+00:00","updated_at":"2026-07-05T10:02:24.149149+00:00"}