{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2VT4JDVHSZX7S4ZTPZR2T36WGP","short_pith_number":"pith:2VT4JDVH","schema_version":"1.0","canonical_sha256":"d567c48ea7966ff973337e63a9efd633eb6ac2ad00de91e65424d8c6bdf09ae4","source":{"kind":"arxiv","id":"2105.01051","version":4},"attestation_state":"computed","paper":{"title":"SUPERB: Speech processing Universal PERformance Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Andy T. Liu, Cheng-I Jeff Lai, Da-Rong Liu, Guan-Ting Lin, Hung-yi Lee, Jiatong Shi, Ko-tik Lee, Kushal Lakhotia, Po-Han Chi, Shang-Wen Li, Shinji Watanabe, Shu-wen Yang, Shuyan Dong, Tzu-hsien Huang, Wei-Cheng Tseng, Xuankai Chang, Yist Y. Lin, Yung-Sung Chuang, Zili Huang","submitted_at":"2021-05-03T17:51:09Z","abstract_excerpt":"Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks"},"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":"2105.01051","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-03T17:51:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fce8d21e4e7a2a3271bc6fc2f53442cd1158f7ef2e28829d85584ab404e7304c","abstract_canon_sha256":"7dfff9540248c6d7fc1d5032d8c31d6ab9e0590773532b269ff743972978c8e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:10.134305Z","signature_b64":"uZ9cxhRq0uG8Jyf1m42/jjwu6qiBI357kLUfMzeVRn19MndITgqs9YSl/pIXVzuh23uPKBGi/L+r6u5Qp02+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d567c48ea7966ff973337e63a9efd633eb6ac2ad00de91e65424d8c6bdf09ae4","last_reissued_at":"2026-07-05T03:23:10.133825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:10.133825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUPERB: Speech processing Universal PERformance Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Andy T. Liu, Cheng-I Jeff Lai, Da-Rong Liu, Guan-Ting Lin, Hung-yi Lee, Jiatong Shi, Ko-tik Lee, Kushal Lakhotia, Po-Han Chi, Shang-Wen Li, Shinji Watanabe, Shu-wen Yang, Shuyan Dong, Tzu-hsien Huang, Wei-Cheng Tseng, Xuankai Chang, Yist Y. Lin, Yung-Sung Chuang, Zili Huang","submitted_at":"2021-05-03T17:51:09Z","abstract_excerpt":"Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01051","kind":"arxiv","version":4},"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/2105.01051/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":"2105.01051","created_at":"2026-07-05T03:23:10.133883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01051v4","created_at":"2026-07-05T03:23:10.133883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01051","created_at":"2026-07-05T03:23:10.133883+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VT4JDVHSZX7","created_at":"2026-07-05T03:23:10.133883+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VT4JDVHSZX7S4ZT","created_at":"2026-07-05T03:23:10.133883+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VT4JDVH","created_at":"2026-07-05T03:23:10.133883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22868","citing_title":"MSU-Bench: Towards Speaker-Centric Understanding in Conversational Multi-Speaker Scenarios","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24910","citing_title":"End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21210","citing_title":"Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19398","citing_title":"S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06837","citing_title":"SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01802","citing_title":"MOSS-Audio Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30899","citing_title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30550","citing_title":"SIGMA: Saliency-Guided Sparse Mask Attacks for Speech Emotion Recognition","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21210","citing_title":"Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22765","citing_title":"StressTest: Can YOUR Speech LM Handle the Stress?","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11845","citing_title":"AVEX: What Matters for Animal Vocalization Encoding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08470","citing_title":"Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14231","citing_title":"AudioMosaic: Contrastive Masked Audio Representation Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10494","citing_title":"Multi-layer attentive probing improves transfer of audio representations for bioacoustics","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00251","citing_title":"Alethia: A Foundational Encoder for Voice Deepfakes","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06702","citing_title":"ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP","json":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP.json","graph_json":"https://pith.science/api/pith-number/2VT4JDVHSZX7S4ZTPZR2T36WGP/graph.json","events_json":"https://pith.science/api/pith-number/2VT4JDVHSZX7S4ZTPZR2T36WGP/events.json","paper":"https://pith.science/paper/2VT4JDVH"},"agent_actions":{"view_html":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP","download_json":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP.json","view_paper":"https://pith.science/paper/2VT4JDVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01051&json=true","fetch_graph":"https://pith.science/api/pith-number/2VT4JDVHSZX7S4ZTPZR2T36WGP/graph.json","fetch_events":"https://pith.science/api/pith-number/2VT4JDVHSZX7S4ZTPZR2T36WGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP/action/storage_attestation","attest_author":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP/action/author_attestation","sign_citation":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP/action/citation_signature","submit_replication":"https://pith.science/pith/2VT4JDVHSZX7S4ZTPZR2T36WGP/action/replication_record"}},"created_at":"2026-07-05T03:23:10.133883+00:00","updated_at":"2026-07-05T03:23:10.133883+00:00"}