{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3DM5KTBPYLPCOUV2ZOU3KWT2IZ","short_pith_number":"pith:3DM5KTBP","schema_version":"1.0","canonical_sha256":"d8d9d54c2fc2de2752bacba9b55a7a467a77ef39cc23958a06e8c77d0a8a7a1a","source":{"kind":"arxiv","id":"2408.12734","version":1},"attestation_state":"computed","paper":{"title":"Towards measuring fairness in speech recognition: Fair-Speech dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.AI","authors_text":"Fuchun Peng, Irina-Elena Veliche, Michael L. Seltzer, Ozlem Kalinli, Vineeth Ayyat Kochaniyan, Zhuangqun Huang","submitted_at":"2024-08-22T20:55:17Z","abstract_excerpt":"The current public datasets for speech recognition (ASR) tend not to focus specifically on the fairness aspect, such as performance across different demographic groups. This paper introduces a novel dataset, Fair-Speech, a publicly released corpus to help researchers evaluate their ASR models for accuracy across a diverse set of self-reported demographic information, such as age, gender, ethnicity, geographic variation and whether the participants consider themselves native English speakers. Our dataset includes approximately 26.5K utterances in recorded speech by 593 people in the United Stat"},"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":"2408.12734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T20:55:17Z","cross_cats_sorted":["cs.CY","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"7e8edd6d5076f276074beb732b0503e6c9f4a4e746905f4f1dc328c610f7335a","abstract_canon_sha256":"ac4e1a731f8332869480593163834ef9c5f5945b5dc93050f04df2dd57053485"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:29.489386Z","signature_b64":"EGR59+ASlhdVGCHPGUN8n4FY2BVT+F8jWyH6KmFllkLFpc8aCgMIQfOmPJ4uAw+zNmRJgfWWTpAHM5u0M/jdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8d9d54c2fc2de2752bacba9b55a7a467a77ef39cc23958a06e8c77d0a8a7a1a","last_reissued_at":"2026-07-05T08:58:29.488888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:29.488888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards measuring fairness in speech recognition: Fair-Speech dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.AI","authors_text":"Fuchun Peng, Irina-Elena Veliche, Michael L. Seltzer, Ozlem Kalinli, Vineeth Ayyat Kochaniyan, Zhuangqun Huang","submitted_at":"2024-08-22T20:55:17Z","abstract_excerpt":"The current public datasets for speech recognition (ASR) tend not to focus specifically on the fairness aspect, such as performance across different demographic groups. This paper introduces a novel dataset, Fair-Speech, a publicly released corpus to help researchers evaluate their ASR models for accuracy across a diverse set of self-reported demographic information, such as age, gender, ethnicity, geographic variation and whether the participants consider themselves native English speakers. Our dataset includes approximately 26.5K utterances in recorded speech by 593 people in the United Stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12734","kind":"arxiv","version":1},"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/2408.12734/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":"2408.12734","created_at":"2026-07-05T08:58:29.488947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12734v1","created_at":"2026-07-05T08:58:29.488947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12734","created_at":"2026-07-05T08:58:29.488947+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DM5KTBPYLPC","created_at":"2026-07-05T08:58:29.488947+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DM5KTBPYLPCOUV2","created_at":"2026-07-05T08:58:29.488947+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DM5KTBP","created_at":"2026-07-05T08:58:29.488947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11639","citing_title":"Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10503","citing_title":"Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05830","citing_title":"\"OK Aura, Be Fair With Me\": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ","json":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ.json","graph_json":"https://pith.science/api/pith-number/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/graph.json","events_json":"https://pith.science/api/pith-number/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/events.json","paper":"https://pith.science/paper/3DM5KTBP"},"agent_actions":{"view_html":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ","download_json":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ.json","view_paper":"https://pith.science/paper/3DM5KTBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12734&json=true","fetch_graph":"https://pith.science/api/pith-number/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/action/storage_attestation","attest_author":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/action/author_attestation","sign_citation":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/action/citation_signature","submit_replication":"https://pith.science/pith/3DM5KTBPYLPCOUV2ZOU3KWT2IZ/action/replication_record"}},"created_at":"2026-07-05T08:58:29.488947+00:00","updated_at":"2026-07-05T08:58:29.488947+00:00"}