{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ODAWM5ZWDBK3GXE7MDHKUQZXOK","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":"15fcf3eae500e3c002227e5308df0054098eed8202473cb1ea2bb3133b0c5c81","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-21T09:07:11Z","title_canon_sha256":"0b90cf44c6cf84d5f27a66665f829d99b7f0d44d008e6dc1c916b46f154d52e8"},"schema_version":"1.0","source":{"id":"2311.12454","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12454","created_at":"2026-07-05T07:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12454v2","created_at":"2026-07-05T07:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12454","created_at":"2026-07-05T07:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"ODAWM5ZWDBK3","created_at":"2026-07-05T07:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"ODAWM5ZWDBK3GXE7","created_at":"2026-07-05T07:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"ODAWM5ZW","created_at":"2026-07-05T07:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:460f446c1dd7c2f1708cada0a765eea5839d608f05b72b08dd579db3c8c47916","target":"graph","created_at":"2026-07-05T07:16:50Z","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/2311.12454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLM)-based speech synthesis has been widely adopted in zero-shot speech synthesis. However, they require a large-scale data and possess the same limitations as previous autoregressive speech models, including slow inference speed and lack of robustness. This paper proposes HierSpeech++, a fast and strong zero-shot speech synthesizer for text-to-speech (TTS) and voice conversion (VC). We verified that hierarchical speech synthesis frameworks could significantly improve the robustness and expressiveness of the synthetic speech. Furthermore, we significantly improve the nat","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee, Seung-Bin Kim","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-21T09:07:11Z","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12454","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:ce35fd5ffb9bf2c726827b5f5e08e52f93dd7aedc1f323ef1d40c72e58426980","target":"record","created_at":"2026-07-05T07:16:50Z","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":"15fcf3eae500e3c002227e5308df0054098eed8202473cb1ea2bb3133b0c5c81","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-21T09:07:11Z","title_canon_sha256":"0b90cf44c6cf84d5f27a66665f829d99b7f0d44d008e6dc1c916b46f154d52e8"},"schema_version":"1.0","source":{"id":"2311.12454","kind":"arxiv","version":2}},"canonical_sha256":"70c16677361855b35c9f60ceaa4337729e2b1784f6524ddb18e3980cf751cbc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70c16677361855b35c9f60ceaa4337729e2b1784f6524ddb18e3980cf751cbc5","first_computed_at":"2026-07-05T07:16:50.673624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:50.673624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z2tkSgVpaIf6AlZ+6KN7rUYuuvFDlTYelUk8iUIfZ10zY0EMrhoklpAVjNyLyDqyb5qPqAk9OZeqp95r0JWEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:50.674078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12454","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce35fd5ffb9bf2c726827b5f5e08e52f93dd7aedc1f323ef1d40c72e58426980","sha256:460f446c1dd7c2f1708cada0a765eea5839d608f05b72b08dd579db3c8c47916"],"state_sha256":"e2a0a01259e13ee5310de5333078fe687472f5ae890fe53376f7a2999c7f471b"}