{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RZ6QQ35GND3TQQI3FRLQL2XZP3","short_pith_number":"pith:RZ6QQ35G","schema_version":"1.0","canonical_sha256":"8e7d086fa668f738411b2c5705eaf97ed7286c2c621674e53f47f22a35652328","source":{"kind":"arxiv","id":"2606.17662","version":1},"attestation_state":"computed","paper":{"title":"An Analysis of the Effectiveness of Synthetic Speech Data for ASR Fine-tuning in Selected Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar, Pranav Bhat, Prasanta Kumar Ghosh, Sujith Pulikodan, Visruth Sanka","submitted_at":"2026-06-16T08:26:09Z","abstract_excerpt":"Synthetic data has the potential to be a valuable resource for training machine learning models, particularly Automatic Speech Recognition (ASR) Systems; however, its effectiveness requires systematic evaluation. In this study, we investigate the impact of incorporating synthetic speech data alongside real-world recordings for three Indic languages: Hindi, Kannada, and Telugu. We analyze the performance gains achieved by augmenting synthetic data with real data and independently examine how ASR performance varies with the sources of scripts used to generate synthetic speech. In addition, we ev"},"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":"2606.17662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T08:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"f1f243707e679aed505e0a1fd39a915972ca5385ce5b04b6c2b8a6aa1ef548a6","abstract_canon_sha256":"631d39de52fb58e3c2d8d479e36e782df78d9c5f99f78fc6a29e3f945a58d25a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:18.593999Z","signature_b64":"TDnKjEG2XqxnFJv/cQROU+yQr3DIZxcaiNzaRUSPodTC3Uj77Zcy8j43jkeN90WOVgINsoq92sye9ibgVEUnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e7d086fa668f738411b2c5705eaf97ed7286c2c621674e53f47f22a35652328","last_reissued_at":"2026-06-19T16:10:18.593601Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:18.593601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of the Effectiveness of Synthetic Speech Data for ASR Fine-tuning in Selected Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Agneedh Basu, Nihar Desai, Pavan Kumar, Pranav Bhat, Prasanta Kumar Ghosh, Sujith Pulikodan, Visruth Sanka","submitted_at":"2026-06-16T08:26:09Z","abstract_excerpt":"Synthetic data has the potential to be a valuable resource for training machine learning models, particularly Automatic Speech Recognition (ASR) Systems; however, its effectiveness requires systematic evaluation. In this study, we investigate the impact of incorporating synthetic speech data alongside real-world recordings for three Indic languages: Hindi, Kannada, and Telugu. We analyze the performance gains achieved by augmenting synthetic data with real data and independently examine how ASR performance varies with the sources of scripts used to generate synthetic speech. In addition, we ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17662","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/2606.17662/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":"2606.17662","created_at":"2026-06-19T16:10:18.593663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17662v1","created_at":"2026-06-19T16:10:18.593663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17662","created_at":"2026-06-19T16:10:18.593663+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZ6QQ35GND3T","created_at":"2026-06-19T16:10:18.593663+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZ6QQ35GND3TQQI3","created_at":"2026-06-19T16:10:18.593663+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZ6QQ35G","created_at":"2026-06-19T16:10:18.593663+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/RZ6QQ35GND3TQQI3FRLQL2XZP3","json":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3.json","graph_json":"https://pith.science/api/pith-number/RZ6QQ35GND3TQQI3FRLQL2XZP3/graph.json","events_json":"https://pith.science/api/pith-number/RZ6QQ35GND3TQQI3FRLQL2XZP3/events.json","paper":"https://pith.science/paper/RZ6QQ35G"},"agent_actions":{"view_html":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3","download_json":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3.json","view_paper":"https://pith.science/paper/RZ6QQ35G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17662&json=true","fetch_graph":"https://pith.science/api/pith-number/RZ6QQ35GND3TQQI3FRLQL2XZP3/graph.json","fetch_events":"https://pith.science/api/pith-number/RZ6QQ35GND3TQQI3FRLQL2XZP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3/action/storage_attestation","attest_author":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3/action/author_attestation","sign_citation":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3/action/citation_signature","submit_replication":"https://pith.science/pith/RZ6QQ35GND3TQQI3FRLQL2XZP3/action/replication_record"}},"created_at":"2026-06-19T16:10:18.593663+00:00","updated_at":"2026-06-19T16:10:18.593663+00:00"}