{"paper":{"title":"Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A controlled pairwise evaluation framework allows reliable ranking of TTS systems for ten Indian languages by collecting multi-dimensional judgments from native speakers.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaditya Pareek, Adish Pandya, Ashwin Sankar, Deepon Halder, Gaurav Yadav, Ishvinder Sethi, Kartik Rajput, Mitesh M Khapra, Mohammed Safi Ur Rahman Khan, Nikhil Narasimhan, Praveen S V, Shobhit Banga, Srija Anand","submitted_at":"2026-04-23T09:44:03Z","abstract_excerpt":"Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to Speech(TTS) introduces high variance due to linguistic diversity and multidimensional nature of speech perception. We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation. Using 5K+ native and code-mixed sentences across 10 Indic languages, we evaluate 7 state-of-the-art TTS systems and collect over 120K pairwise comparisons from over 1900 native raters. In "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 120K pairwise comparisons from 1900 native raters, despite acknowledged high variance in speech perception, yield reliable signals for Bradley-Terry leaderboard construction and SHAP interpretation after linguistic controls.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A controlled pairwise evaluation framework for multilingual TTS in 10 Indic languages produces a preference leaderboard using Bradley-Terry modeling and SHAP analysis on 120K+ comparisons.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A controlled pairwise evaluation framework allows reliable ranking of TTS systems for ten Indian languages by collecting multi-dimensional judgments from native speakers.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"78ddbe22e34efcfbd6aeda4f8831553801572dbf65a93b724d5671cf2e4378e7"},"source":{"id":"2604.21481","kind":"arxiv","version":2},"verdict":{"id":"cbff0601-a686-43d4-8b76-45aebeed7aa1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T22:04:56.068757Z","strongest_claim":"We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation.","one_line_summary":"A controlled pairwise evaluation framework for multilingual TTS in 10 Indic languages produces a preference leaderboard using Bradley-Terry modeling and SHAP analysis on 120K+ comparisons.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 120K pairwise comparisons from 1900 native raters, despite acknowledged high variance in speech perception, yield reliable signals for Bradley-Terry leaderboard construction and SHAP interpretation after linguistic controls.","pith_extraction_headline":"A controlled pairwise evaluation framework allows reliable ranking of TTS systems for ten Indian languages by collecting multi-dimensional judgments from native speakers."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.21481/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T12:40:52.967609Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T00:57:11.414892Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"dd694260007003f221b6225f442bb5a62a4a36988f4829e3c41d260416f51476"},"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"}