{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYV5OATRCUF6QKJ2ZCW5CESBPH","short_pith_number":"pith:DYV5OATR","schema_version":"1.0","canonical_sha256":"1e2bd70271150be8293ac8add1124179e466bb55134e00dc784d90a300839739","source":{"kind":"arxiv","id":"2409.05356","version":2},"attestation_state":"computed","paper":{"title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"cs.CL","authors_text":"Aditi Krishana, Ashwin Sankar, Deovrat Mehendale, Giri Raju, Mehak Singal, Mitesh Khapra, Praveen Srinivasa Varadhan, Sherry Thomas, Shridhar Kumar, Srija Anand","submitted_at":"2024-09-09T06:28:47Z","abstract_excerpt":"Recent advancements in text-to-speech (TTS) synthesis show that large-scale models trained with extensive web data produce highly natural-sounding output. However, such data is scarce for Indian languages due to the lack of high-quality, manually subtitled data on platforms like LibriVox or YouTube. To address this gap, we enhance existing large-scale ASR datasets containing natural conversations collected in low-quality environments to generate high-quality TTS training data. Our pipeline leverages the cross-lingual generalization of denoising and speech enhancement models trained on English "},"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":"2409.05356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T06:28:47Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"title_canon_sha256":"c03c63c968e3d6c6d1d79a649782576c4215e0479a5ad94a7985b06b21054863","abstract_canon_sha256":"5b626fc9117119967ffaab4d1fa162ca2302920f62fd1904b5f32d223c601cbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:52.333850Z","signature_b64":"69BqiY4kpbgmS4WZk2SCK+uHDdmkloIgf38jOhxTX8hYKBOHOmGQmGkYIoixoaRhtOu77bam39T3nC71pg1vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e2bd70271150be8293ac8add1124179e466bb55134e00dc784d90a300839739","last_reissued_at":"2026-07-05T09:16:52.333389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:52.333389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"cs.CL","authors_text":"Aditi Krishana, Ashwin Sankar, Deovrat Mehendale, Giri Raju, Mehak Singal, Mitesh Khapra, Praveen Srinivasa Varadhan, Sherry Thomas, Shridhar Kumar, Srija Anand","submitted_at":"2024-09-09T06:28:47Z","abstract_excerpt":"Recent advancements in text-to-speech (TTS) synthesis show that large-scale models trained with extensive web data produce highly natural-sounding output. However, such data is scarce for Indian languages due to the lack of high-quality, manually subtitled data on platforms like LibriVox or YouTube. To address this gap, we enhance existing large-scale ASR datasets containing natural conversations collected in low-quality environments to generate high-quality TTS training data. Our pipeline leverages the cross-lingual generalization of denoising and speech enhancement models trained on English "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05356","kind":"arxiv","version":2},"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/2409.05356/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":"2409.05356","created_at":"2026-07-05T09:16:52.333447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05356v2","created_at":"2026-07-05T09:16:52.333447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05356","created_at":"2026-07-05T09:16:52.333447+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYV5OATRCUF6","created_at":"2026-07-05T09:16:52.333447+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYV5OATRCUF6QKJ2","created_at":"2026-07-05T09:16:52.333447+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYV5OATR","created_at":"2026-07-05T09:16:52.333447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16875","citing_title":"Technical report: Impact of Duration Prediction on Speaker-specific TTS for Indian Languages","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH","json":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH.json","graph_json":"https://pith.science/api/pith-number/DYV5OATRCUF6QKJ2ZCW5CESBPH/graph.json","events_json":"https://pith.science/api/pith-number/DYV5OATRCUF6QKJ2ZCW5CESBPH/events.json","paper":"https://pith.science/paper/DYV5OATR"},"agent_actions":{"view_html":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH","download_json":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH.json","view_paper":"https://pith.science/paper/DYV5OATR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05356&json=true","fetch_graph":"https://pith.science/api/pith-number/DYV5OATRCUF6QKJ2ZCW5CESBPH/graph.json","fetch_events":"https://pith.science/api/pith-number/DYV5OATRCUF6QKJ2ZCW5CESBPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/action/storage_attestation","attest_author":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/action/author_attestation","sign_citation":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/action/citation_signature","submit_replication":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/action/replication_record"}},"created_at":"2026-07-05T09:16:52.333447+00:00","updated_at":"2026-07-05T09:16:52.333447+00:00"}