{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P7Y6VUPRTVEL5A5ATWSSQ7KNAZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4bd734e39b58759c61db14f39c972f1c1f850bdf0d27802db5e6f736c7bcb140","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T07:10:25Z","title_canon_sha256":"2c5ba7cbbd3fbcfa20c68d6288d915a726e8c01a0630289a2771ae86ddfe78bc"},"schema_version":"1.0","source":{"id":"2410.03192","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03192","created_at":"2026-07-05T09:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03192v1","created_at":"2026-07-05T09:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03192","created_at":"2026-07-05T09:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"P7Y6VUPRTVEL","created_at":"2026-07-05T09:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"P7Y6VUPRTVEL5A5A","created_at":"2026-07-05T09:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"P7Y6VUPR","created_at":"2026-07-05T09:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:e950e568da1938e33792eb66a4d179c494660a237479657fc94bc6e7612a3118","target":"graph","created_at":"2026-07-05T09:15:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.03192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-speech (TTS) systems that scale up the amount of training data have achieved significant improvements in zero-shot speech synthesis. However, these systems have certain limitations: they require a large amount of training data, which increases costs, and often overlook prosody similarity. To address these issues, we propose MultiVerse, a zero-shot multi-task TTS system that is able to perform TTS or speech style transfer in zero-shot and cross-lingual conditions. MultiVerse requires much less training data than traditional data-driven approaches. To ensure zero-shot performance even wi","authors_text":"SeungJae Choi, Taejun Bak, Youngsik Eom, Young-Sun Joo","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T07:10:25Z","title":"MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03192","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1853e74689f0957ebe01de1a6d0608a97677214b09042850d89c429ac8716af5","target":"record","created_at":"2026-07-05T09:15:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4bd734e39b58759c61db14f39c972f1c1f850bdf0d27802db5e6f736c7bcb140","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T07:10:25Z","title_canon_sha256":"2c5ba7cbbd3fbcfa20c68d6288d915a726e8c01a0630289a2771ae86ddfe78bc"},"schema_version":"1.0","source":{"id":"2410.03192","kind":"arxiv","version":1}},"canonical_sha256":"7ff1ead1f19d48be83a09da5287d4d065920285c134abd6b37e44d4b4c41653c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ff1ead1f19d48be83a09da5287d4d065920285c134abd6b37e44d4b4c41653c","first_computed_at":"2026-07-05T09:15:45.984763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:45.984763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zrIM6e8RAffJFi7W+IHqm/LhN28R+SCpGbz8CI9h8RG0/aAbl4Bnb+zCqM9owKWPZhIkewzl6Gcg6QxuExqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:45.985211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03192","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1853e74689f0957ebe01de1a6d0608a97677214b09042850d89c429ac8716af5","sha256:e950e568da1938e33792eb66a4d179c494660a237479657fc94bc6e7612a3118"],"state_sha256":"02c1a458886f1980d75541dc1a6c734c2c53d6f460b555c2f602444d820523af"}