{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QO2HBI4WYL267QXIZPLGP77PRC","short_pith_number":"pith:QO2HBI4W","schema_version":"1.0","canonical_sha256":"83b470a396c2f5efc2e8cbd667ffef88a461d2def9ff19c7b3da68b144573b69","source":{"kind":"arxiv","id":"2309.13860","version":2},"attestation_state":"computed","paper":{"title":"Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Guanrou Yang, Xie Chen, Yakun Song, Zhikang Niu, Zhisheng Zheng, Ziyang Ma","submitted_at":"2023-09-25T04:07:34Z","abstract_excerpt":"Recent years have witnessed significant advancements in self-supervised learning (SSL) methods for speech-processing tasks. Various speech-based SSL models have been developed and present promising performance on a range of downstream tasks including speech recognition. However, existing speech-based SSL models face a common dilemma in terms of computational cost, which might hinder their potential application and in-depth academic research. To address this issue, we first analyze the computational cost of different modules during HuBERT pre-training and then introduce a stack of efficiency op"},"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":"2309.13860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T04:07:34Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"d793726b077b4a06ef45852486404f59021ee842b6f9156b28d34c38de155414","abstract_canon_sha256":"cd5e5aa8ac0d74cd229c8a5f6e0e6048cf906fe4258fb7cc08cdc6bbd8b50915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:25.199464Z","signature_b64":"YRIRNisV8MoSmOY6bKK68fiIXnSi3K5ZvRmQesbXnHfsRClrgJy/qzs75yqbC2W/5zgw8zZJHWcrQou8lNslAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83b470a396c2f5efc2e8cbd667ffef88a461d2def9ff19c7b3da68b144573b69","last_reissued_at":"2026-07-05T06:55:25.198996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:25.198996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Guanrou Yang, Xie Chen, Yakun Song, Zhikang Niu, Zhisheng Zheng, Ziyang Ma","submitted_at":"2023-09-25T04:07:34Z","abstract_excerpt":"Recent years have witnessed significant advancements in self-supervised learning (SSL) methods for speech-processing tasks. Various speech-based SSL models have been developed and present promising performance on a range of downstream tasks including speech recognition. However, existing speech-based SSL models face a common dilemma in terms of computational cost, which might hinder their potential application and in-depth academic research. To address this issue, we first analyze the computational cost of different modules during HuBERT pre-training and then introduce a stack of efficiency op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13860","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/2309.13860/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":"2309.13860","created_at":"2026-07-05T06:55:25.199051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13860v2","created_at":"2026-07-05T06:55:25.199051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13860","created_at":"2026-07-05T06:55:25.199051+00:00"},{"alias_kind":"pith_short_12","alias_value":"QO2HBI4WYL26","created_at":"2026-07-05T06:55:25.199051+00:00"},{"alias_kind":"pith_short_16","alias_value":"QO2HBI4WYL267QXI","created_at":"2026-07-05T06:55:25.199051+00:00"},{"alias_kind":"pith_short_8","alias_value":"QO2HBI4W","created_at":"2026-07-05T06:55:25.199051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00988","citing_title":"A Unified Denoising and Adaptation Framework for Self-Supervised Bengali Dialectal ASR","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC","json":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC.json","graph_json":"https://pith.science/api/pith-number/QO2HBI4WYL267QXIZPLGP77PRC/graph.json","events_json":"https://pith.science/api/pith-number/QO2HBI4WYL267QXIZPLGP77PRC/events.json","paper":"https://pith.science/paper/QO2HBI4W"},"agent_actions":{"view_html":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC","download_json":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC.json","view_paper":"https://pith.science/paper/QO2HBI4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13860&json=true","fetch_graph":"https://pith.science/api/pith-number/QO2HBI4WYL267QXIZPLGP77PRC/graph.json","fetch_events":"https://pith.science/api/pith-number/QO2HBI4WYL267QXIZPLGP77PRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC/action/storage_attestation","attest_author":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC/action/author_attestation","sign_citation":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC/action/citation_signature","submit_replication":"https://pith.science/pith/QO2HBI4WYL267QXIZPLGP77PRC/action/replication_record"}},"created_at":"2026-07-05T06:55:25.199051+00:00","updated_at":"2026-07-05T06:55:25.199051+00:00"}