{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P7Y6VUPRTVEL5A5ATWSSQ7KNAZ","short_pith_number":"pith:P7Y6VUPR","schema_version":"1.0","canonical_sha256":"7ff1ead1f19d48be83a09da5287d4d065920285c134abd6b37e44d4b4c41653c","source":{"kind":"arxiv","id":"2410.03192","version":1},"attestation_state":"computed","paper":{"title":"MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"SeungJae Choi, Taejun Bak, Youngsik Eom, Young-Sun Joo","submitted_at":"2024-10-04T07:10:25Z","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"},"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":"2410.03192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T07:10:25Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"2c5ba7cbbd3fbcfa20c68d6288d915a726e8c01a0630289a2771ae86ddfe78bc","abstract_canon_sha256":"4bd734e39b58759c61db14f39c972f1c1f850bdf0d27802db5e6f736c7bcb140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:45.985211Z","signature_b64":"8zrIM6e8RAffJFi7W+IHqm/LhN28R+SCpGbz8CI9h8RG0/aAbl4Bnb+zCqM9owKWPZhIkewzl6Gcg6QxuExqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ff1ead1f19d48be83a09da5287d4d065920285c134abd6b37e44d4b4c41653c","last_reissued_at":"2026-07-05T09:15:45.984763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:45.984763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"SeungJae Choi, Taejun Bak, Youngsik Eom, Young-Sun Joo","submitted_at":"2024-10-04T07:10:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03192","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/2410.03192/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":"2410.03192","created_at":"2026-07-05T09:15:45.984826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03192v1","created_at":"2026-07-05T09:15:45.984826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03192","created_at":"2026-07-05T09:15:45.984826+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7Y6VUPRTVEL","created_at":"2026-07-05T09:15:45.984826+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7Y6VUPRTVEL5A5A","created_at":"2026-07-05T09:15:45.984826+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7Y6VUPR","created_at":"2026-07-05T09:15:45.984826+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/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ","json":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ.json","graph_json":"https://pith.science/api/pith-number/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/graph.json","events_json":"https://pith.science/api/pith-number/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/events.json","paper":"https://pith.science/paper/P7Y6VUPR"},"agent_actions":{"view_html":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ","download_json":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ.json","view_paper":"https://pith.science/paper/P7Y6VUPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03192&json=true","fetch_graph":"https://pith.science/api/pith-number/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/action/storage_attestation","attest_author":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/action/author_attestation","sign_citation":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/action/citation_signature","submit_replication":"https://pith.science/pith/P7Y6VUPRTVEL5A5ATWSSQ7KNAZ/action/replication_record"}},"created_at":"2026-07-05T09:15:45.984826+00:00","updated_at":"2026-07-05T09:15:45.984826+00:00"}