{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WC6NCKSIZ7FNKZUPA5Y62FUSNV","short_pith_number":"pith:WC6NCKSI","schema_version":"1.0","canonical_sha256":"b0bcd12a48cfcad5668f0771ed16926d753fd0aa06499e596fa24810e7699624","source":{"kind":"arxiv","id":"2404.09385","version":2},"attestation_state":"computed","paper":{"title":"A Large-Scale Evaluation of Speech Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.SP"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Andy T. Liu, Cheng-I Lai, Haibin Wu, Heng-Jui Chang, Hsiang-Sheng Tsai, Hung-yi Lee, Jiatong Shi, Kushal Lakhotia, Po-Han Chi, Shang-Wen Li, Shinji Watanabe, Shu-wen Yang, Tzu-hsien Huang, Tzu-hsun Feng, Wei-Cheng Tseng, Wen-Chin Huang, Xuankai Chang, Yist Y. Lin, Yung-Sung Chuang, Zili Huang","submitted_at":"2024-04-15T00:03:16Z","abstract_excerpt":"The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech. We propose a unified multi-tasking framework to address speech proce"},"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":"2404.09385","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-15T00:03:16Z","cross_cats_sorted":["cs.CL","eess.SP"],"title_canon_sha256":"e8c3a527464bbfc771768d94b5cf64b5fe16a76dc85b8548b19700309112c9b2","abstract_canon_sha256":"7755b3e0ac328d2ca2c53f36e9fdb00dbed0f3d57544de12f20fc1ccf5b00e68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:02.824615Z","signature_b64":"mr6bhddDirBmRlXvQZvw5gn3ByFdtR3pRcY/otbg2sGZsBAAWUFZRpG0hpKd9BuyZ4Ucm9jyt/YlNGorwC+QCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0bcd12a48cfcad5668f0771ed16926d753fd0aa06499e596fa24810e7699624","last_reissued_at":"2026-07-05T08:25:02.824025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:02.824025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Evaluation of Speech Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.SP"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Andy T. Liu, Cheng-I Lai, Haibin Wu, Heng-Jui Chang, Hsiang-Sheng Tsai, Hung-yi Lee, Jiatong Shi, Kushal Lakhotia, Po-Han Chi, Shang-Wen Li, Shinji Watanabe, Shu-wen Yang, Tzu-hsien Huang, Tzu-hsun Feng, Wei-Cheng Tseng, Wen-Chin Huang, Xuankai Chang, Yist Y. Lin, Yung-Sung Chuang, Zili Huang","submitted_at":"2024-04-15T00:03:16Z","abstract_excerpt":"The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech. We propose a unified multi-tasking framework to address speech proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09385","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/2404.09385/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":"2404.09385","created_at":"2026-07-05T08:25:02.824087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09385v2","created_at":"2026-07-05T08:25:02.824087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09385","created_at":"2026-07-05T08:25:02.824087+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC6NCKSIZ7FN","created_at":"2026-07-05T08:25:02.824087+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC6NCKSIZ7FNKZUP","created_at":"2026-07-05T08:25:02.824087+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC6NCKSI","created_at":"2026-07-05T08:25:02.824087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16490","citing_title":"HPP-Voice: A Large-Scale Evaluation of Speech Embeddings for Multi-Phenotypic Classification","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV","json":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV.json","graph_json":"https://pith.science/api/pith-number/WC6NCKSIZ7FNKZUPA5Y62FUSNV/graph.json","events_json":"https://pith.science/api/pith-number/WC6NCKSIZ7FNKZUPA5Y62FUSNV/events.json","paper":"https://pith.science/paper/WC6NCKSI"},"agent_actions":{"view_html":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV","download_json":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV.json","view_paper":"https://pith.science/paper/WC6NCKSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09385&json=true","fetch_graph":"https://pith.science/api/pith-number/WC6NCKSIZ7FNKZUPA5Y62FUSNV/graph.json","fetch_events":"https://pith.science/api/pith-number/WC6NCKSIZ7FNKZUPA5Y62FUSNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV/action/storage_attestation","attest_author":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV/action/author_attestation","sign_citation":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV/action/citation_signature","submit_replication":"https://pith.science/pith/WC6NCKSIZ7FNKZUPA5Y62FUSNV/action/replication_record"}},"created_at":"2026-07-05T08:25:02.824087+00:00","updated_at":"2026-07-05T08:25:02.824087+00:00"}