{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4O7PED4DW7OLAXIOMRCBREKLC","short_pith_number":"pith:B4O7PED4","schema_version":"1.0","canonical_sha256":"0f1df7907c1dbee582e8732220c48a58ad1ae1528ad2d6f4595fbd74e37ef669","source":{"kind":"arxiv","id":"2403.01926","version":1},"attestation_state":"computed","paper":{"title":"IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ambujavalli R, Aparna Ananthanarayanan, C Venkata Vaijayanthi, Deovrat Mehendale, Eldho Ittan George, Hafsah Faquih, Ishvinder Virender Sethi, Janki Atul Nawale, Kaushal Santosh Bhogale, Krishnan Srinivasa Raghavan Karunganni, Kunal Sharad Gandhi, Manickam K M, Mitesh M Khapra, Pratiti Palit, Pratyush Kumar, Sakshi Joshi, Saranya Sukumaran, Sneha Ravishankar, Sunjay Murali, Tahir Javed, Tripura Panchagnula","submitted_at":"2024-03-04T10:42:08Z","abstract_excerpt":"We present INDICVOICES, a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speakers covering 145 Indian districts and 22 languages. Of these 7348 hours, 1639 hours have already been transcribed, with a median of 73 hours per language. Through this paper, we share our journey of capturing the cultural, linguistic and demographic diversity of India to create a one-of-its-kind inclusive and representative dataset. More specifically, we share an open-source blueprint for data collection at scale compr"},"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":"2403.01926","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T10:42:08Z","cross_cats_sorted":[],"title_canon_sha256":"2dd125997496ca4d801d49ac12dd20ae14f3ba7e8e46634a7d4f6e10fbe35d9c","abstract_canon_sha256":"9296f53a2b49dda2bff4723286a804d9710959738c281cf34b7991ad8266ff97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:54.188082Z","signature_b64":"kOf/LGltUlbOJFBzhNnkN4X5jSliuFufeW6fh8SpbqBy/smEXsBus0HX7uy0q2hBmk2stPEvyyvRY7u10tyCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1df7907c1dbee582e8732220c48a58ad1ae1528ad2d6f4595fbd74e37ef669","last_reissued_at":"2026-07-05T07:51:54.187623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:54.187623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ambujavalli R, Aparna Ananthanarayanan, C Venkata Vaijayanthi, Deovrat Mehendale, Eldho Ittan George, Hafsah Faquih, Ishvinder Virender Sethi, Janki Atul Nawale, Kaushal Santosh Bhogale, Krishnan Srinivasa Raghavan Karunganni, Kunal Sharad Gandhi, Manickam K M, Mitesh M Khapra, Pratiti Palit, Pratyush Kumar, Sakshi Joshi, Saranya Sukumaran, Sneha Ravishankar, Sunjay Murali, Tahir Javed, Tripura Panchagnula","submitted_at":"2024-03-04T10:42:08Z","abstract_excerpt":"We present INDICVOICES, a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speakers covering 145 Indian districts and 22 languages. Of these 7348 hours, 1639 hours have already been transcribed, with a median of 73 hours per language. Through this paper, we share our journey of capturing the cultural, linguistic and demographic diversity of India to create a one-of-its-kind inclusive and representative dataset. More specifically, we share an open-source blueprint for data collection at scale compr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01926","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/2403.01926/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":"2403.01926","created_at":"2026-07-05T07:51:54.187682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01926v1","created_at":"2026-07-05T07:51:54.187682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01926","created_at":"2026-07-05T07:51:54.187682+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4O7PED4DW7O","created_at":"2026-07-05T07:51:54.187682+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4O7PED4DW7OLAXI","created_at":"2026-07-05T07:51:54.187682+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4O7PED4","created_at":"2026-07-05T07:51:54.187682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26901","citing_title":"SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19151","citing_title":"Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC","json":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC.json","graph_json":"https://pith.science/api/pith-number/B4O7PED4DW7OLAXIOMRCBREKLC/graph.json","events_json":"https://pith.science/api/pith-number/B4O7PED4DW7OLAXIOMRCBREKLC/events.json","paper":"https://pith.science/paper/B4O7PED4"},"agent_actions":{"view_html":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC","download_json":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC.json","view_paper":"https://pith.science/paper/B4O7PED4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01926&json=true","fetch_graph":"https://pith.science/api/pith-number/B4O7PED4DW7OLAXIOMRCBREKLC/graph.json","fetch_events":"https://pith.science/api/pith-number/B4O7PED4DW7OLAXIOMRCBREKLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC/action/storage_attestation","attest_author":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC/action/author_attestation","sign_citation":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC/action/citation_signature","submit_replication":"https://pith.science/pith/B4O7PED4DW7OLAXIOMRCBREKLC/action/replication_record"}},"created_at":"2026-07-05T07:51:54.187682+00:00","updated_at":"2026-07-05T07:51:54.187682+00:00"}