{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DYV5OATRCUF6QKJ2ZCW5CESBPH","short_pith_number":"pith:DYV5OATR","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"},"canonical_sha256":"1e2bd70271150be8293ac8add1124179e466bb55134e00dc784d90a300839739","source":{"kind":"arxiv","id":"2409.05356","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05356","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05356v2","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05356","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"DYV5OATRCUF6","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"DYV5OATRCUF6QKJ2","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"DYV5OATR","created_at":"2026-07-05T09:16:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DYV5OATRCUF6QKJ2ZCW5CESBPH","target":"record","payload":{"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"},"canonical_sha256":"1e2bd70271150be8293ac8add1124179e466bb55134e00dc784d90a300839739","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"},"source_kind":"arxiv","source_id":"2409.05356","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnTDyJvT0XJ1q6FnowwiudBe5B+gCZKu205tdHgzzuLuG7gNJa3lmZNgvtsvg/v8tort2E0gZy9fbGnWr6+KBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:12:12.192349Z"},"content_sha256":"19e8bfc7a2bb4ac782aefe47a06aea02b706a56a21b97e5c068e679b7c77bccd","schema_version":"1.0","event_id":"sha256:19e8bfc7a2bb4ac782aefe47a06aea02b706a56a21b97e5c068e679b7c77bccd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DYV5OATRCUF6QKJ2ZCW5CESBPH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNd3KwjVZOuiN5sHxHSbI2AVK9d3uLGjtntRsGHDCtXFSUgl7QIJFnaCOYTVu8Jql0WXP7wcvlAZV192s7NZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:12:12.192702Z"},"content_sha256":"8a75da2f001066235a66cadd1d1cf4ec47169e3cfa3c6f09e1a6593a91c0cb11","schema_version":"1.0","event_id":"sha256:8a75da2f001066235a66cadd1d1cf4ec47169e3cfa3c6f09e1a6593a91c0cb11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/bundle.json","state_url":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T14:12:12Z","links":{"resolver":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH","bundle":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/bundle.json","state":"https://pith.science/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYV5OATRCUF6QKJ2ZCW5CESBPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DYV5OATRCUF6QKJ2ZCW5CESBPH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b626fc9117119967ffaab4d1fa162ca2302920f62fd1904b5f32d223c601cbb","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T06:28:47Z","title_canon_sha256":"c03c63c968e3d6c6d1d79a649782576c4215e0479a5ad94a7985b06b21054863"},"schema_version":"1.0","source":{"id":"2409.05356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05356","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05356v2","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05356","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"DYV5OATRCUF6","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"DYV5OATRCUF6QKJ2","created_at":"2026-07-05T09:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"DYV5OATR","created_at":"2026-07-05T09:16:52Z"}],"graph_snapshots":[{"event_id":"sha256:8a75da2f001066235a66cadd1d1cf4ec47169e3cfa3c6f09e1a6593a91c0cb11","target":"graph","created_at":"2026-07-05T09:16:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.05356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aditi Krishana, Ashwin Sankar, Deovrat Mehendale, Giri Raju, Mehak Singal, Mitesh Khapra, Praveen Srinivasa Varadhan, Sherry Thomas, Shridhar Kumar, Srija Anand","cross_cats":["cs.LG","cs.SD","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T06:28:47Z","title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05356","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:19e8bfc7a2bb4ac782aefe47a06aea02b706a56a21b97e5c068e679b7c77bccd","target":"record","created_at":"2026-07-05T09:16:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b626fc9117119967ffaab4d1fa162ca2302920f62fd1904b5f32d223c601cbb","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T06:28:47Z","title_canon_sha256":"c03c63c968e3d6c6d1d79a649782576c4215e0479a5ad94a7985b06b21054863"},"schema_version":"1.0","source":{"id":"2409.05356","kind":"arxiv","version":2}},"canonical_sha256":"1e2bd70271150be8293ac8add1124179e466bb55134e00dc784d90a300839739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e2bd70271150be8293ac8add1124179e466bb55134e00dc784d90a300839739","first_computed_at":"2026-07-05T09:16:52.333389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:52.333389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"69BqiY4kpbgmS4WZk2SCK+uHDdmkloIgf38jOhxTX8hYKBOHOmGQmGkYIoixoaRhtOu77bam39T3nC71pg1vDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:52.333850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19e8bfc7a2bb4ac782aefe47a06aea02b706a56a21b97e5c068e679b7c77bccd","sha256:8a75da2f001066235a66cadd1d1cf4ec47169e3cfa3c6f09e1a6593a91c0cb11"],"state_sha256":"2265df915aa23ecc7bf511fbec62aecdb5ebe7cfeb35e619f752d5cd12ce1c88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v/RJkIzCi6badK5Ab1vAakKCOfqcUAJB07dHYGXtclBFo/1qQzR1nkDXyZNBqVzkfK9hu/4QcfruIrCikwWFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:12:12.197178Z","bundle_sha256":"16ba40745fd90d73d4989c304ffbbda1e20218fcc74db7950d8a9868336987e3"}}