{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2JUE4WUAG4NV3G2H5ITCMOS7XT","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":"62a73df23b5fcbbb4f7f1d78b175ac2d58ab7ba0d37a18459b4dcc11ee251061","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-04T21:33:56Z","title_canon_sha256":"69843293af1bfa0ceef4278a34dfe2ead98333a2d5fcd76dfd92ff0ab55bad57"},"schema_version":"1.0","source":{"id":"2411.02625","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02625","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02625v2","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02625","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"2JUE4WUAG4NV","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"2JUE4WUAG4NV3G2H","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"2JUE4WUA","created_at":"2026-07-05T10:50:10Z"}],"graph_snapshots":[{"event_id":"sha256:3f06cb5f39837002e6366cd0b0790e75a67c4c4618c9cbeb11ac4e3042a9d2e8","target":"graph","created_at":"2026-07-05T10:50:10Z","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/2411.02625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotional text-to-speech (TTS) technology has achieved significant progress in recent years; however, challenges remain owing to the inherent complexity of emotions and limitations of the available emotional speech datasets and models. Previous studies typically relied on limited emotional speech datasets or required extensive manual annotations, restricting their ability to generalize across different speakers and emotional styles. In this paper, we present EmoSphere++, an emotion-controllable zero-shot TTS model that can control emotional style and intensity to resemble natural human speech.","authors_text":"Deok-Hyeon Cho, Hyung-Seok Oh, Seong-Whan Lee, Seung-Bin Kim","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-04T21:33:56Z","title":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02625","kind":"arxiv","version":2},"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":"sha256:262eed4ffbf6608e6035ea140d967fa1295b711b328fe5f75baad7851925b896","target":"record","created_at":"2026-07-05T10:50:10Z","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":"62a73df23b5fcbbb4f7f1d78b175ac2d58ab7ba0d37a18459b4dcc11ee251061","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-04T21:33:56Z","title_canon_sha256":"69843293af1bfa0ceef4278a34dfe2ead98333a2d5fcd76dfd92ff0ab55bad57"},"schema_version":"1.0","source":{"id":"2411.02625","kind":"arxiv","version":2}},"canonical_sha256":"d2684e5a80371b5d9b47ea26263a5fbcce2f36c50234b68ecbef8c8626f2342b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2684e5a80371b5d9b47ea26263a5fbcce2f36c50234b68ecbef8c8626f2342b","first_computed_at":"2026-07-05T10:50:10.136646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:10.136646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xFrRRiYRn8eVV5SIVsJggaX9/EWPs2hMkRwHiK89XNsTx2gQBGc0xDjyvTnnyVnTwhbbrcyGd6hkSPdNHcf1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:10.137072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02625","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:262eed4ffbf6608e6035ea140d967fa1295b711b328fe5f75baad7851925b896","sha256:3f06cb5f39837002e6366cd0b0790e75a67c4c4618c9cbeb11ac4e3042a9d2e8"],"state_sha256":"b81b4a5125e2dcd7c8b936a296ca3d94c4e48234b357592ed8ea1529b3a68e69"}