{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PXAOFR6APLJQQXGTJPB4VWAH7D","short_pith_number":"pith:PXAOFR6A","schema_version":"1.0","canonical_sha256":"7dc0e2c7c07ad3085cd34bc3cad807f8f212148db2b5ad84b9f04d215256deb7","source":{"kind":"arxiv","id":"2410.17901","version":1},"attestation_state":"computed","paper":{"title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Mehak Singal, Mitesh M. Khapra, Praveen Srinivasa Varadhan, Srija Anand","submitted_at":"2024-10-23T14:18:25Z","abstract_excerpt":"Recent advancements in Text-to-Speech (TTS) technology have led to natural-sounding speech for English, primarily due to the availability of large-scale, high-quality web data. However, many other languages lack access to such resources, relying instead on limited studio-quality data. This scarcity results in synthesized speech that often suffers from intelligibility issues, particularly with low-frequency character bigrams. In this paper, we propose three solutions to address this challenge. First, we leverage high-quality data from linguistically or geographically related languages to improv"},"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":"2410.17901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T14:18:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ab99fa303dfc7bfe7030bac5f734479cd120a075bc448531b3796d3967e06b2e","abstract_canon_sha256":"7f5671a50b8bffde882a4c063fd710b1fd036da6d0fb538e123d790782277c74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:46.538557Z","signature_b64":"j2qLfg+DULRj9WLIAHvrJA3ex9FUoNsnoxrld4mXz7r1blNSsKcXu06exbY6z42tGZYx+DEX7vpVTMyJkBB6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc0e2c7c07ad3085cd34bc3cad807f8f212148db2b5ad84b9f04d215256deb7","last_reissued_at":"2026-07-05T09:24:46.538067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:46.538067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Mehak Singal, Mitesh M. Khapra, Praveen Srinivasa Varadhan, Srija Anand","submitted_at":"2024-10-23T14:18:25Z","abstract_excerpt":"Recent advancements in Text-to-Speech (TTS) technology have led to natural-sounding speech for English, primarily due to the availability of large-scale, high-quality web data. However, many other languages lack access to such resources, relying instead on limited studio-quality data. This scarcity results in synthesized speech that often suffers from intelligibility issues, particularly with low-frequency character bigrams. In this paper, we propose three solutions to address this challenge. First, we leverage high-quality data from linguistically or geographically related languages to improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17901","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/2410.17901/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":"2410.17901","created_at":"2026-07-05T09:24:46.538125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17901v1","created_at":"2026-07-05T09:24:46.538125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17901","created_at":"2026-07-05T09:24:46.538125+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXAOFR6APLJQ","created_at":"2026-07-05T09:24:46.538125+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXAOFR6APLJQQXGT","created_at":"2026-07-05T09:24:46.538125+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXAOFR6A","created_at":"2026-07-05T09:24:46.538125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21481","citing_title":"Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D","json":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D.json","graph_json":"https://pith.science/api/pith-number/PXAOFR6APLJQQXGTJPB4VWAH7D/graph.json","events_json":"https://pith.science/api/pith-number/PXAOFR6APLJQQXGTJPB4VWAH7D/events.json","paper":"https://pith.science/paper/PXAOFR6A"},"agent_actions":{"view_html":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D","download_json":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D.json","view_paper":"https://pith.science/paper/PXAOFR6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17901&json=true","fetch_graph":"https://pith.science/api/pith-number/PXAOFR6APLJQQXGTJPB4VWAH7D/graph.json","fetch_events":"https://pith.science/api/pith-number/PXAOFR6APLJQQXGTJPB4VWAH7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D/action/storage_attestation","attest_author":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D/action/author_attestation","sign_citation":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D/action/citation_signature","submit_replication":"https://pith.science/pith/PXAOFR6APLJQQXGTJPB4VWAH7D/action/replication_record"}},"created_at":"2026-07-05T09:24:46.538125+00:00","updated_at":"2026-07-05T09:24:46.538125+00:00"}