{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FIGJSHZSPTYG7WUG7X7I4ILGYW","short_pith_number":"pith:FIGJSHZS","schema_version":"1.0","canonical_sha256":"2a0c991f327cf06fda86fdfe8e2166c59b8670023ee309202bbfea63ab21ffc7","source":{"kind":"arxiv","id":"2305.09688","version":1},"attestation_state":"computed","paper":{"title":"OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Ahmed Imtiaz Humayun, Asif Sushmit, Farig Sadeque, Fazle Rabbi Rakib, Mamunur Mamun, Marsia Haque Meghla, Md. Istiak Hossain Shihab, MD. Nazmuddoha Ansary, Nazia Tasnim, Samiul Alam, Sayma Sultana Chowdhury, Souhardya Saha Dip, Syed Mobassir Hossen, Tahsin Reasat","submitted_at":"2023-05-15T18:00:39Z","abstract_excerpt":"We present OOD-Speech, the first out-of-distribution (OOD) benchmarking dataset for Bengali automatic speech recognition (ASR). Being one of the most spoken languages globally, Bengali portrays large diversity in dialects and prosodic features, which demands ASR frameworks to be robust towards distribution shifts. For example, islamic religious sermons in Bengali are delivered with a tonality that is significantly different from regular speech. Our training dataset is collected via massively online crowdsourcing campaigns which resulted in 1177.94 hours collected and curated from $22,645$ nati"},"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":"2305.09688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-15T18:00:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"21b044c896eaa8532d07d0a8cd283156cafafde9aec78b944bb55ed23674ca34","abstract_canon_sha256":"52e023da59a507d039cfd9a6700e6d08b3594691314416b0e1ba1a9e40683c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:52.743348Z","signature_b64":"EO5CZPuWDC7h9VSt/j/MHYIKeTjwKElXrTKWKs+Ds9dMJ9rId2m8OpsMQ+IC0d0O9Mrl7mM1oRUkISuNX0HlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a0c991f327cf06fda86fdfe8e2166c59b8670023ee309202bbfea63ab21ffc7","last_reissued_at":"2026-07-05T06:10:52.742881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:52.742881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Ahmed Imtiaz Humayun, Asif Sushmit, Farig Sadeque, Fazle Rabbi Rakib, Mamunur Mamun, Marsia Haque Meghla, Md. Istiak Hossain Shihab, MD. Nazmuddoha Ansary, Nazia Tasnim, Samiul Alam, Sayma Sultana Chowdhury, Souhardya Saha Dip, Syed Mobassir Hossen, Tahsin Reasat","submitted_at":"2023-05-15T18:00:39Z","abstract_excerpt":"We present OOD-Speech, the first out-of-distribution (OOD) benchmarking dataset for Bengali automatic speech recognition (ASR). Being one of the most spoken languages globally, Bengali portrays large diversity in dialects and prosodic features, which demands ASR frameworks to be robust towards distribution shifts. For example, islamic religious sermons in Bengali are delivered with a tonality that is significantly different from regular speech. Our training dataset is collected via massively online crowdsourcing campaigns which resulted in 1177.94 hours collected and curated from $22,645$ nati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09688","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/2305.09688/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":"2305.09688","created_at":"2026-07-05T06:10:52.742937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09688v1","created_at":"2026-07-05T06:10:52.742937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09688","created_at":"2026-07-05T06:10:52.742937+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIGJSHZSPTYG","created_at":"2026-07-05T06:10:52.742937+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIGJSHZSPTYG7WUG","created_at":"2026-07-05T06:10:52.742937+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIGJSHZS","created_at":"2026-07-05T06:10:52.742937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24244","citing_title":"When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW","json":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW.json","graph_json":"https://pith.science/api/pith-number/FIGJSHZSPTYG7WUG7X7I4ILGYW/graph.json","events_json":"https://pith.science/api/pith-number/FIGJSHZSPTYG7WUG7X7I4ILGYW/events.json","paper":"https://pith.science/paper/FIGJSHZS"},"agent_actions":{"view_html":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW","download_json":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW.json","view_paper":"https://pith.science/paper/FIGJSHZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09688&json=true","fetch_graph":"https://pith.science/api/pith-number/FIGJSHZSPTYG7WUG7X7I4ILGYW/graph.json","fetch_events":"https://pith.science/api/pith-number/FIGJSHZSPTYG7WUG7X7I4ILGYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW/action/storage_attestation","attest_author":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW/action/author_attestation","sign_citation":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW/action/citation_signature","submit_replication":"https://pith.science/pith/FIGJSHZSPTYG7WUG7X7I4ILGYW/action/replication_record"}},"created_at":"2026-07-05T06:10:52.742937+00:00","updated_at":"2026-07-05T06:10:52.742937+00:00"}