{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WNMEMZDXL755QLL3ZGMA6NHMIW","short_pith_number":"pith:WNMEMZDX","schema_version":"1.0","canonical_sha256":"b3584664775ffbd82d7bc9980f34ec45a0e2c18907c7928e0407949b03c63340","source":{"kind":"arxiv","id":"2305.15760","version":1},"attestation_state":"computed","paper":{"title":"Svarah: Evaluating English ASR Systems on Indian Accents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Janki Nawale, Kaushal Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sai Sundaresan, Sakshi Joshi, Tahir Javed, Vignesh Nagarajan","submitted_at":"2023-05-25T06:20:29Z","abstract_excerpt":"India is the second largest English-speaking country in the world with a speaker base of roughly 130 million. Thus, it is imperative that automatic speech recognition (ASR) systems for English should be evaluated on Indian accents. Unfortunately, Indian speakers find a very poor representation in existing English ASR benchmarks such as LibriSpeech, Switchboard, Speech Accent Archive, etc. In this work, we address this gap by creating Svarah, a benchmark that contains 9.6 hours of transcribed English audio from 117 speakers across 65 geographic locations throughout India, resulting in a diverse"},"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":"2305.15760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T06:20:29Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"37f972aff74e420fdabe02e1b054601387208a6a2c2e1b74d73ea91c8d713a5b","abstract_canon_sha256":"53b5a2552fa0b0d5ff022df807ce09be8b35066f67a22500808b7515b9e67170"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:44.413795Z","signature_b64":"RqucngBfWUaeU12161WRp/rRF1lj9YXN5E0tx9or2D8IZ8EcLlqOnbsy0VyT8jG+e38sy0qa3llVZ3nLF1DTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3584664775ffbd82d7bc9980f34ec45a0e2c18907c7928e0407949b03c63340","last_reissued_at":"2026-07-05T06:13:44.413292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:44.413292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Svarah: Evaluating English ASR Systems on Indian Accents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Janki Nawale, Kaushal Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sai Sundaresan, Sakshi Joshi, Tahir Javed, Vignesh Nagarajan","submitted_at":"2023-05-25T06:20:29Z","abstract_excerpt":"India is the second largest English-speaking country in the world with a speaker base of roughly 130 million. Thus, it is imperative that automatic speech recognition (ASR) systems for English should be evaluated on Indian accents. Unfortunately, Indian speakers find a very poor representation in existing English ASR benchmarks such as LibriSpeech, Switchboard, Speech Accent Archive, etc. In this work, we address this gap by creating Svarah, a benchmark that contains 9.6 hours of transcribed English audio from 117 speakers across 65 geographic locations throughout India, resulting in a diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15760","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/2305.15760/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":"2305.15760","created_at":"2026-07-05T06:13:44.413364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15760v1","created_at":"2026-07-05T06:13:44.413364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15760","created_at":"2026-07-05T06:13:44.413364+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNMEMZDXL755","created_at":"2026-07-05T06:13:44.413364+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNMEMZDXL755QLL3","created_at":"2026-07-05T06:13:44.413364+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNMEMZDX","created_at":"2026-07-05T06:13:44.413364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26901","citing_title":"SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW","json":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW.json","graph_json":"https://pith.science/api/pith-number/WNMEMZDXL755QLL3ZGMA6NHMIW/graph.json","events_json":"https://pith.science/api/pith-number/WNMEMZDXL755QLL3ZGMA6NHMIW/events.json","paper":"https://pith.science/paper/WNMEMZDX"},"agent_actions":{"view_html":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW","download_json":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW.json","view_paper":"https://pith.science/paper/WNMEMZDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15760&json=true","fetch_graph":"https://pith.science/api/pith-number/WNMEMZDXL755QLL3ZGMA6NHMIW/graph.json","fetch_events":"https://pith.science/api/pith-number/WNMEMZDXL755QLL3ZGMA6NHMIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW/action/storage_attestation","attest_author":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW/action/author_attestation","sign_citation":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW/action/citation_signature","submit_replication":"https://pith.science/pith/WNMEMZDXL755QLL3ZGMA6NHMIW/action/replication_record"}},"created_at":"2026-07-05T06:13:44.413364+00:00","updated_at":"2026-07-05T06:13:44.413364+00:00"}