{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LT3QH4IW2IUFPJKC4SJBG5RAWS","short_pith_number":"pith:LT3QH4IW","schema_version":"1.0","canonical_sha256":"5cf703f116d22857a542e492137620b49e1bd6337e10fde786a8e2faf9801d04","source":{"kind":"arxiv","id":"2604.21481","version":2},"attestation_state":"computed","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 "},"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":"2604.21481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T09:44:03Z","cross_cats_sorted":[],"title_canon_sha256":"b32fca7258c46766f269ead942be635aa852a0e84ae6cf2e117ead4728d287f5","abstract_canon_sha256":"69a5e62e3443288806254fbbe4c7001fe89e489096e7a26ddac3b04d134da977"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:27.921094Z","signature_b64":"awTqfTZZIqxvEsE+d4JGNm4NkF/oANpiPBTnR8tfgr9mi+r0gk/lfwKN+lJGGdLuTkGEsrpQ7lIRA+ZOmKtKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cf703f116d22857a542e492137620b49e1bd6337e10fde786a8e2faf9801d04","last_reissued_at":"2026-06-24T01:14:27.920603Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:27.920603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.21481","created_at":"2026-06-24T01:14:27.920657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.21481v2","created_at":"2026-06-24T01:14:27.920657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21481","created_at":"2026-06-24T01:14:27.920657+00:00"},{"alias_kind":"pith_short_12","alias_value":"LT3QH4IW2IUF","created_at":"2026-06-24T01:14:27.920657+00:00"},{"alias_kind":"pith_short_16","alias_value":"LT3QH4IW2IUFPJKC","created_at":"2026-06-24T01:14:27.920657+00:00"},{"alias_kind":"pith_short_8","alias_value":"LT3QH4IW","created_at":"2026-06-24T01:14:27.920657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"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":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS","json":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS.json","graph_json":"https://pith.science/api/pith-number/LT3QH4IW2IUFPJKC4SJBG5RAWS/graph.json","events_json":"https://pith.science/api/pith-number/LT3QH4IW2IUFPJKC4SJBG5RAWS/events.json","paper":"https://pith.science/paper/LT3QH4IW"},"agent_actions":{"view_html":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS","download_json":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS.json","view_paper":"https://pith.science/paper/LT3QH4IW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.21481&json=true","fetch_graph":"https://pith.science/api/pith-number/LT3QH4IW2IUFPJKC4SJBG5RAWS/graph.json","fetch_events":"https://pith.science/api/pith-number/LT3QH4IW2IUFPJKC4SJBG5RAWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS/action/storage_attestation","attest_author":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS/action/author_attestation","sign_citation":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS/action/citation_signature","submit_replication":"https://pith.science/pith/LT3QH4IW2IUFPJKC4SJBG5RAWS/action/replication_record"}},"created_at":"2026-06-24T01:14:27.920657+00:00","updated_at":"2026-06-24T01:14:27.920657+00:00"}