{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:INVJOASPEMCVZKZMZPOTGRUJJS","short_pith_number":"pith:INVJOASP","schema_version":"1.0","canonical_sha256":"436a97024f23055cab2ccbdd3346894c8bc10db1b95154f252ccb62037472f1c","source":{"kind":"arxiv","id":"2411.04699","version":3},"attestation_state":"computed","paper":{"title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Ashwin Sankar, Devilal Choudhary, Dhairya Suman, Mitesh M Khapra, Mohammed Safi Ur Rahman Khan, Nikhil Narasimhan, Raj Dabre, Sparsh Jain","submitted_at":"2024-11-07T13:33:34Z","abstract_excerpt":"Speech translation for Indian languages remains a challenging task due to the scarcity of large-scale, publicly available datasets that capture the linguistic diversity and domain coverage essential for real-world applications. Existing datasets cover a fraction of Indian languages and lack the breadth needed to train robust models that generalize beyond curated benchmarks. To bridge this gap, we introduce BhasaAnuvaad, the largest speech translation dataset for Indian languages, spanning over 44 thousand hours of audio and 17 million aligned text segments across 14 Indian languages and Englis"},"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":"2411.04699","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T13:33:34Z","cross_cats_sorted":[],"title_canon_sha256":"92a4e550df9fdf9851a69eb926316058f15b4b84f6463c32fccb391945fb7353","abstract_canon_sha256":"c3d293b2fd2e210110a56589f0db668cbb276e922992592d60b417799a50eb3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:15.362780Z","signature_b64":"rnWOsTnWsFe1t+lArKq/AztroaMyxbXkHSBizQfqeo66nZBjoO8OuOwy0i46CkDAy3UhR1IEMVZ2MLXJGR/pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436a97024f23055cab2ccbdd3346894c8bc10db1b95154f252ccb62037472f1c","last_reissued_at":"2026-07-05T11:13:15.362051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:15.362051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Ashwin Sankar, Devilal Choudhary, Dhairya Suman, Mitesh M Khapra, Mohammed Safi Ur Rahman Khan, Nikhil Narasimhan, Raj Dabre, Sparsh Jain","submitted_at":"2024-11-07T13:33:34Z","abstract_excerpt":"Speech translation for Indian languages remains a challenging task due to the scarcity of large-scale, publicly available datasets that capture the linguistic diversity and domain coverage essential for real-world applications. Existing datasets cover a fraction of Indian languages and lack the breadth needed to train robust models that generalize beyond curated benchmarks. To bridge this gap, we introduce BhasaAnuvaad, the largest speech translation dataset for Indian languages, spanning over 44 thousand hours of audio and 17 million aligned text segments across 14 Indian languages and Englis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04699","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/2411.04699/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":"2411.04699","created_at":"2026-07-05T11:13:15.362138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04699v3","created_at":"2026-07-05T11:13:15.362138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04699","created_at":"2026-07-05T11:13:15.362138+00:00"},{"alias_kind":"pith_short_12","alias_value":"INVJOASPEMCV","created_at":"2026-07-05T11:13:15.362138+00:00"},{"alias_kind":"pith_short_16","alias_value":"INVJOASPEMCVZKZM","created_at":"2026-07-05T11:13:15.362138+00:00"},{"alias_kind":"pith_short_8","alias_value":"INVJOASP","created_at":"2026-07-05T11:13:15.362138+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/INVJOASPEMCVZKZMZPOTGRUJJS","json":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS.json","graph_json":"https://pith.science/api/pith-number/INVJOASPEMCVZKZMZPOTGRUJJS/graph.json","events_json":"https://pith.science/api/pith-number/INVJOASPEMCVZKZMZPOTGRUJJS/events.json","paper":"https://pith.science/paper/INVJOASP"},"agent_actions":{"view_html":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS","download_json":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS.json","view_paper":"https://pith.science/paper/INVJOASP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04699&json=true","fetch_graph":"https://pith.science/api/pith-number/INVJOASPEMCVZKZMZPOTGRUJJS/graph.json","fetch_events":"https://pith.science/api/pith-number/INVJOASPEMCVZKZMZPOTGRUJJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS/action/storage_attestation","attest_author":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS/action/author_attestation","sign_citation":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS/action/citation_signature","submit_replication":"https://pith.science/pith/INVJOASPEMCVZKZMZPOTGRUJJS/action/replication_record"}},"created_at":"2026-07-05T11:13:15.362138+00:00","updated_at":"2026-07-05T11:13:15.362138+00:00"}