{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QMZRRDWLEO5435PRYNTHXCKALV","short_pith_number":"pith:QMZRRDWL","canonical_record":{"source":{"id":"2407.13435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T12:03:14Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"ab8501eeb3a0fbbc4b2899a15e1c645d20bf2ea08d3b2f46d6ce65478ec24d0d","abstract_canon_sha256":"6c21bffdc5a24fa501b040dce6876a5689fcf9da799b2a24ad7cd5aff1c0535c"},"schema_version":"1.0"},"canonical_sha256":"8333188ecb23bbcdf5f1c3667b89405d70d65d94b017eb7867093dfef94124f0","source":{"kind":"arxiv","id":"2407.13435","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13435","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13435v1","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13435","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"QMZRRDWLEO54","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"QMZRRDWLEO5435PR","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"QMZRRDWL","created_at":"2026-07-05T08:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QMZRRDWLEO5435PRYNTHXCKALV","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T12:03:14Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"ab8501eeb3a0fbbc4b2899a15e1c645d20bf2ea08d3b2f46d6ce65478ec24d0d","abstract_canon_sha256":"6c21bffdc5a24fa501b040dce6876a5689fcf9da799b2a24ad7cd5aff1c0535c"},"schema_version":"1.0"},"canonical_sha256":"8333188ecb23bbcdf5f1c3667b89405d70d65d94b017eb7867093dfef94124f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:38.965291Z","signature_b64":"cqqu5Zg3o7V9vYEwFJ+ji24hVstkG3rj7ENnnR8lrMKW30M2hzGmn+lyX6vi3Q6o/55QeTnmIH5Dnu3wwk+9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8333188ecb23bbcdf5f1c3667b89405d70d65d94b017eb7867093dfef94124f0","last_reissued_at":"2026-07-05T08:45:38.964806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:38.964806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13435","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oArYPvyc7aGfdARCCgPoIc3IYmZBHhCsumHFON35daK4kNoscGl/MZvB5kjF+E62TaEtauf/SIWnE9Wp9CpqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:06:29.326120Z"},"content_sha256":"7b298fef73497878fe03f7e7408807da1b66235bc6e4c079c57ddeafea3b5426","schema_version":"1.0","event_id":"sha256:7b298fef73497878fe03f7e7408807da1b66235bc6e4c079c57ddeafea3b5426"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QMZRRDWLEO5435PRYNTHXCKALV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ashwin Sankar, Giri Raju, Mitesh M. Khapra, Praveen Srinivasa Varadhan, Srija Anand","submitted_at":"2024-07-18T12:03:14Z","abstract_excerpt":"Publicly available TTS datasets for low-resource languages like Hindi and Tamil typically contain 10-20 hours of data, leading to poor vocabulary coverage. This limitation becomes evident in downstream applications where domain-specific vocabulary coupled with frequent code-mixing with English, results in many OOV words. To highlight this problem, we create a benchmark containing OOV words from several real-world applications. Indeed, state-of-the-art Hindi and Tamil TTS systems perform poorly on this OOV benchmark, as indicated by intelligibility tests. To improve the model's OOV performance,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13435","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/2407.13435/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":"2026-07-05T08:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"US04MaLNT5knyz2CLg2N5QbdSbKGxBZDDGPKViAqIkwflc+Pd0rd/mcEYFIPrig3RtAZa/APGoz2XR6QtQcwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:06:29.326545Z"},"content_sha256":"1aa886913ef316d2f1837ce451d1c3cb2f709062e0afcf41355be2ed9b52c224","schema_version":"1.0","event_id":"sha256:1aa886913ef316d2f1837ce451d1c3cb2f709062e0afcf41355be2ed9b52c224"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/bundle.json","state_url":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMZRRDWLEO5435PRYNTHXCKALV/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":"2026-07-08T16:06:29Z","links":{"resolver":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV","bundle":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/bundle.json","state":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMZRRDWLEO5435PRYNTHXCKALV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QMZRRDWLEO5435PRYNTHXCKALV","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":"6c21bffdc5a24fa501b040dce6876a5689fcf9da799b2a24ad7cd5aff1c0535c","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T12:03:14Z","title_canon_sha256":"ab8501eeb3a0fbbc4b2899a15e1c645d20bf2ea08d3b2f46d6ce65478ec24d0d"},"schema_version":"1.0","source":{"id":"2407.13435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13435","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13435v1","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13435","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"QMZRRDWLEO54","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"QMZRRDWLEO5435PR","created_at":"2026-07-05T08:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"QMZRRDWL","created_at":"2026-07-05T08:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:1aa886913ef316d2f1837ce451d1c3cb2f709062e0afcf41355be2ed9b52c224","target":"graph","created_at":"2026-07-05T08:45:38Z","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/2407.13435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Publicly available TTS datasets for low-resource languages like Hindi and Tamil typically contain 10-20 hours of data, leading to poor vocabulary coverage. This limitation becomes evident in downstream applications where domain-specific vocabulary coupled with frequent code-mixing with English, results in many OOV words. To highlight this problem, we create a benchmark containing OOV words from several real-world applications. Indeed, state-of-the-art Hindi and Tamil TTS systems perform poorly on this OOV benchmark, as indicated by intelligibility tests. To improve the model's OOV performance,","authors_text":"Ashwin Sankar, Giri Raju, Mitesh M. Khapra, Praveen Srinivasa Varadhan, Srija Anand","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T12:03:14Z","title":"Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13435","kind":"arxiv","version":1},"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":"sha256:7b298fef73497878fe03f7e7408807da1b66235bc6e4c079c57ddeafea3b5426","target":"record","created_at":"2026-07-05T08:45:38Z","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":"6c21bffdc5a24fa501b040dce6876a5689fcf9da799b2a24ad7cd5aff1c0535c","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T12:03:14Z","title_canon_sha256":"ab8501eeb3a0fbbc4b2899a15e1c645d20bf2ea08d3b2f46d6ce65478ec24d0d"},"schema_version":"1.0","source":{"id":"2407.13435","kind":"arxiv","version":1}},"canonical_sha256":"8333188ecb23bbcdf5f1c3667b89405d70d65d94b017eb7867093dfef94124f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8333188ecb23bbcdf5f1c3667b89405d70d65d94b017eb7867093dfef94124f0","first_computed_at":"2026-07-05T08:45:38.964806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:38.964806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cqqu5Zg3o7V9vYEwFJ+ji24hVstkG3rj7ENnnR8lrMKW30M2hzGmn+lyX6vi3Q6o/55QeTnmIH5Dnu3wwk+9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:38.965291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b298fef73497878fe03f7e7408807da1b66235bc6e4c079c57ddeafea3b5426","sha256:1aa886913ef316d2f1837ce451d1c3cb2f709062e0afcf41355be2ed9b52c224"],"state_sha256":"6bc85f584d1f0d3d43c7c22795df40bbbd5b88a2e41e8f2a6d2dc0c331c81d84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bfNzolCyw3LbG8ztunTgxWkNQMWvZwPVUgzq9tTUDy2jqMnzyL/S4Kb5ZkILBKnnhQeACI0XXX/xexlvP/OSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:06:29.328755Z","bundle_sha256":"cc0a5140544ac131901728ff4e11162400623083e95d8fcdbb843d0f57ce4cf7"}}