{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QMZRRDWLEO5435PRYNTHXCKALV","short_pith_number":"pith:QMZRRDWL","schema_version":"1.0","canonical_sha256":"8333188ecb23bbcdf5f1c3667b89405d70d65d94b017eb7867093dfef94124f0","source":{"kind":"arxiv","id":"2407.13435","version":1},"attestation_state":"computed","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,"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.13435","created_at":"2026-07-05T08:45:38.964864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13435v1","created_at":"2026-07-05T08:45:38.964864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13435","created_at":"2026-07-05T08:45:38.964864+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMZRRDWLEO54","created_at":"2026-07-05T08:45:38.964864+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMZRRDWLEO5435PR","created_at":"2026-07-05T08:45:38.964864+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMZRRDWL","created_at":"2026-07-05T08:45:38.964864+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/QMZRRDWLEO5435PRYNTHXCKALV","json":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV.json","graph_json":"https://pith.science/api/pith-number/QMZRRDWLEO5435PRYNTHXCKALV/graph.json","events_json":"https://pith.science/api/pith-number/QMZRRDWLEO5435PRYNTHXCKALV/events.json","paper":"https://pith.science/paper/QMZRRDWL"},"agent_actions":{"view_html":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV","download_json":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV.json","view_paper":"https://pith.science/paper/QMZRRDWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13435&json=true","fetch_graph":"https://pith.science/api/pith-number/QMZRRDWLEO5435PRYNTHXCKALV/graph.json","fetch_events":"https://pith.science/api/pith-number/QMZRRDWLEO5435PRYNTHXCKALV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/action/storage_attestation","attest_author":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/action/author_attestation","sign_citation":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/action/citation_signature","submit_replication":"https://pith.science/pith/QMZRRDWLEO5435PRYNTHXCKALV/action/replication_record"}},"created_at":"2026-07-05T08:45:38.964864+00:00","updated_at":"2026-07-05T08:45:38.964864+00:00"}