{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LZC43PAMHYG564HSKG33ZAOXJG","short_pith_number":"pith:LZC43PAM","schema_version":"1.0","canonical_sha256":"5e45cdbc0c3e0ddf70f251b7bc81d749ab1213437f52171d705b28d9298d5fe2","source":{"kind":"arxiv","id":"2505.18609","version":2},"attestation_state":"computed","paper":{"title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashwin Sankar, Mitesh M Khapra, Praveen Srinivasa Varadhan, Sanchit Gandhi, Sherry Thomas, Yoach Lacombe","submitted_at":"2025-05-24T09:16:14Z","abstract_excerpt":"We introduce RASMALAI, a large-scale speech dataset with rich text descriptions, designed to advance controllable and expressive text-to-speech (TTS) synthesis for 23 Indian languages and English. It comprises 13,000 hours of speech and 24 million text-description annotations with fine-grained attributes like speaker identity, accent, emotion, style, and background conditions. Using RASMALAI, we develop IndicParlerTTS, the first open-source, text-description-guided TTS for Indian languages. Systematic evaluation demonstrates its ability to generate high-quality speech for named speakers, relia"},"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":"2505.18609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T09:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"1edd9e9ba034488d9461e47b5961c010b031697100734db5d352476a0aeeaa14","abstract_canon_sha256":"d9d17a3130aa39ec806baa54453ae1165d7bd08e9d0b287581b9c97161a03ddb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:38.298832Z","signature_b64":"8vrBdpZ5JVjEKrYkg5aIxS3JRS0NT1M+VmvtXbtkOnnWf4AMm8qUcVWRTR++QfCY2EDex2A6osIphH9ELySsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e45cdbc0c3e0ddf70f251b7bc81d749ab1213437f52171d705b28d9298d5fe2","last_reissued_at":"2026-07-05T11:10:38.298305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:38.298305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashwin Sankar, Mitesh M Khapra, Praveen Srinivasa Varadhan, Sanchit Gandhi, Sherry Thomas, Yoach Lacombe","submitted_at":"2025-05-24T09:16:14Z","abstract_excerpt":"We introduce RASMALAI, a large-scale speech dataset with rich text descriptions, designed to advance controllable and expressive text-to-speech (TTS) synthesis for 23 Indian languages and English. It comprises 13,000 hours of speech and 24 million text-description annotations with fine-grained attributes like speaker identity, accent, emotion, style, and background conditions. Using RASMALAI, we develop IndicParlerTTS, the first open-source, text-description-guided TTS for Indian languages. Systematic evaluation demonstrates its ability to generate high-quality speech for named speakers, relia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18609","kind":"arxiv","version":2},"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/2505.18609/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":"2505.18609","created_at":"2026-07-05T11:10:38.298381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18609v2","created_at":"2026-07-05T11:10:38.298381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18609","created_at":"2026-07-05T11:10:38.298381+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZC43PAMHYG5","created_at":"2026-07-05T11:10:38.298381+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZC43PAMHYG564HS","created_at":"2026-07-05T11:10:38.298381+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZC43PAM","created_at":"2026-07-05T11:10:38.298381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18609","citing_title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG","json":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG.json","graph_json":"https://pith.science/api/pith-number/LZC43PAMHYG564HSKG33ZAOXJG/graph.json","events_json":"https://pith.science/api/pith-number/LZC43PAMHYG564HSKG33ZAOXJG/events.json","paper":"https://pith.science/paper/LZC43PAM"},"agent_actions":{"view_html":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG","download_json":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG.json","view_paper":"https://pith.science/paper/LZC43PAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18609&json=true","fetch_graph":"https://pith.science/api/pith-number/LZC43PAMHYG564HSKG33ZAOXJG/graph.json","fetch_events":"https://pith.science/api/pith-number/LZC43PAMHYG564HSKG33ZAOXJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG/action/storage_attestation","attest_author":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG/action/author_attestation","sign_citation":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG/action/citation_signature","submit_replication":"https://pith.science/pith/LZC43PAMHYG564HSKG33ZAOXJG/action/replication_record"}},"created_at":"2026-07-05T11:10:38.298381+00:00","updated_at":"2026-07-05T11:10:38.298381+00:00"}