{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ETH6I3R5KCCQRIC5B4HTNT5IA3","short_pith_number":"pith:ETH6I3R5","schema_version":"1.0","canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","source":{"kind":"arxiv","id":"2203.16595","version":3},"attestation_state":"computed","paper":{"title":"Improving Speech Recognition for Indic Languages using Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anirudh Gupta, Ankur Dhuriya, Harveen Singh Chadha, Neeraj Chhimwal, Priyanshi Shah, Rishabh Gaur, Vivek Raghavan","submitted_at":"2022-03-30T18:22:12Z","abstract_excerpt":"We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec $2.0$ models for $18$ Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over $28$ \\% and the average Word Error Rate (WER) decreases by about $36$ \\% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high q"},"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":"2203.16595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T18:22:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"36b09071a168680f998dc3b63e4747154c405fa93e9c737c25ba19bb852f3346","abstract_canon_sha256":"8193229ae8bf7acdb38eee5ed5961ee3552f6b8954a57e0aee6ee4c0126d6ba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:59.926832Z","signature_b64":"3pMhDrGJ2gjAeN+9xZLNcoYNBXALCDpMqouSENbHioy88A2+2Yqa9k2DMB/9RbLvOdmsmzrGQ/LsjQytfrCYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","last_reissued_at":"2026-07-05T04:31:59.926393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:59.926393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Speech Recognition for Indic Languages using Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anirudh Gupta, Ankur Dhuriya, Harveen Singh Chadha, Neeraj Chhimwal, Priyanshi Shah, Rishabh Gaur, Vivek Raghavan","submitted_at":"2022-03-30T18:22:12Z","abstract_excerpt":"We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec $2.0$ models for $18$ Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over $28$ \\% and the average Word Error Rate (WER) decreases by about $36$ \\% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16595","kind":"arxiv","version":3},"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/2203.16595/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":"2203.16595","created_at":"2026-07-05T04:31:59.926450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16595v3","created_at":"2026-07-05T04:31:59.926450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16595","created_at":"2026-07-05T04:31:59.926450+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETH6I3R5KCCQ","created_at":"2026-07-05T04:31:59.926450+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETH6I3R5KCCQRIC5","created_at":"2026-07-05T04:31:59.926450+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETH6I3R5","created_at":"2026-07-05T04:31:59.926450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3","json":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3.json","graph_json":"https://pith.science/api/pith-number/ETH6I3R5KCCQRIC5B4HTNT5IA3/graph.json","events_json":"https://pith.science/api/pith-number/ETH6I3R5KCCQRIC5B4HTNT5IA3/events.json","paper":"https://pith.science/paper/ETH6I3R5"},"agent_actions":{"view_html":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3","download_json":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3.json","view_paper":"https://pith.science/paper/ETH6I3R5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16595&json=true","fetch_graph":"https://pith.science/api/pith-number/ETH6I3R5KCCQRIC5B4HTNT5IA3/graph.json","fetch_events":"https://pith.science/api/pith-number/ETH6I3R5KCCQRIC5B4HTNT5IA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/action/storage_attestation","attest_author":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/action/author_attestation","sign_citation":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/action/citation_signature","submit_replication":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/action/replication_record"}},"created_at":"2026-07-05T04:31:59.926450+00:00","updated_at":"2026-07-05T04:31:59.926450+00:00"}