{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UJQ5BD555HPHV4YOCSJH2TDOUF","short_pith_number":"pith:UJQ5BD55","schema_version":"1.0","canonical_sha256":"a261d08fbde9de7af30e14927d4c6ea14954524d34e5055e32c1dde7f440f8a6","source":{"kind":"arxiv","id":"2605.20830","version":1},"attestation_state":"computed","paper":{"title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongmin Park, Jaewoong Cho, Kangwook Lee, Keon Lee, Ludwig Schmidt, Minyoung Ahn, Nam Soo Kim, Sangheon Lee, Semin Kim, Seungjun Chung, Taehong Moon","submitted_at":"2026-05-20T07:21:36Z","abstract_excerpt":"Recent advances in text-to-speech (TTS) models show impressive speech naturalness and quality, yet the role of large-scale open data in driving this progress remains underexplored. In this work, we introduce Raon-OpenTTS, an open TTS model that performs competitively with state-of-the-art closed-data TTS models, and Raon-OpenTTS-Pool, a large-scale open dataset for reproducible TTS training. Raon-OpenTTS-Pool consists of 615K hours of 240M speech segments aggregated from publicly available English speech corpora and web-sourced recordings. With a model-based filtering pipeline applied to Raon-"},"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":"2605.20830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-20T07:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"1bd9af9a154a5b8e465ce4b301cc0e5610e7e8eaba933004d43f6d72dfca5c35","abstract_canon_sha256":"7ce07fb13287d070629d0a66d71f46bdd50df90ea7c3151ccf5e7af30a772c95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:23.492271Z","signature_b64":"9f7TlGgVqf8zPGCi+Fk2s8A1nTPdLWhuEfAaN0oy1L47IiZub1GyaYY/X2OQ6kZn4/aEa33xlvj6Pj/3rRr7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a261d08fbde9de7af30e14927d4c6ea14954524d34e5055e32c1dde7f440f8a6","last_reissued_at":"2026-05-21T01:05:23.491386Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:23.491386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongmin Park, Jaewoong Cho, Kangwook Lee, Keon Lee, Ludwig Schmidt, Minyoung Ahn, Nam Soo Kim, Sangheon Lee, Semin Kim, Seungjun Chung, Taehong Moon","submitted_at":"2026-05-20T07:21:36Z","abstract_excerpt":"Recent advances in text-to-speech (TTS) models show impressive speech naturalness and quality, yet the role of large-scale open data in driving this progress remains underexplored. In this work, we introduce Raon-OpenTTS, an open TTS model that performs competitively with state-of-the-art closed-data TTS models, and Raon-OpenTTS-Pool, a large-scale open dataset for reproducible TTS training. Raon-OpenTTS-Pool consists of 615K hours of 240M speech segments aggregated from publicly available English speech corpora and web-sourced recordings. With a model-based filtering pipeline applied to Raon-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20830","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/2605.20830/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":"2605.20830","created_at":"2026-05-21T01:05:23.491488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20830v1","created_at":"2026-05-21T01:05:23.491488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20830","created_at":"2026-05-21T01:05:23.491488+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJQ5BD555HPH","created_at":"2026-05-21T01:05:23.491488+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJQ5BD555HPHV4YO","created_at":"2026-05-21T01:05:23.491488+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJQ5BD55","created_at":"2026-05-21T01:05:23.491488+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/UJQ5BD555HPHV4YOCSJH2TDOUF","json":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF.json","graph_json":"https://pith.science/api/pith-number/UJQ5BD555HPHV4YOCSJH2TDOUF/graph.json","events_json":"https://pith.science/api/pith-number/UJQ5BD555HPHV4YOCSJH2TDOUF/events.json","paper":"https://pith.science/paper/UJQ5BD55"},"agent_actions":{"view_html":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF","download_json":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF.json","view_paper":"https://pith.science/paper/UJQ5BD55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20830&json=true","fetch_graph":"https://pith.science/api/pith-number/UJQ5BD555HPHV4YOCSJH2TDOUF/graph.json","fetch_events":"https://pith.science/api/pith-number/UJQ5BD555HPHV4YOCSJH2TDOUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF/action/storage_attestation","attest_author":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF/action/author_attestation","sign_citation":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF/action/citation_signature","submit_replication":"https://pith.science/pith/UJQ5BD555HPHV4YOCSJH2TDOUF/action/replication_record"}},"created_at":"2026-05-21T01:05:23.491488+00:00","updated_at":"2026-05-21T01:05:23.491488+00:00"}