{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G46JPUQU2XDAQKIZURDNJZ4BMX","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":"38261b51448bdb67a48e4dd30f9190ba7d63601b99bdbf864d14ea7290944622","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":"2023-07-30T08:49:55Z","title_canon_sha256":"9d883b7d55d6cd17d0a1e68b018015fe3a37bb66b43b05da3c54f037c2a76124"},"schema_version":"1.0","source":{"id":"2307.16171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16171","created_at":"2026-07-05T06:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16171v1","created_at":"2026-07-05T06:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16171","created_at":"2026-07-05T06:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"G46JPUQU2XDA","created_at":"2026-07-05T06:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"G46JPUQU2XDAQKIZ","created_at":"2026-07-05T06:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"G46JPUQU","created_at":"2026-07-05T06:35:59Z"}],"graph_snapshots":[{"event_id":"sha256:e1b62fade34b25204cee2cbfcc63e0a8fe355790d19648324746b58304eaaa4a","target":"graph","created_at":"2026-07-05T06:35:59Z","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/2307.16171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress in the voice style transfer (VST) field, recent zero-shot VST systems still lack the ability to transfer the voice style of a novel speaker. In this paper, we present HierVST, a hierarchical adaptive end-to-end zero-shot VST model. Without any text transcripts, we only use the speech dataset to train the model by utilizing hierarchical variational inference and self-supervised representation. In addition, we adopt a hierarchical adaptive generator that generates the pitch representation and waveform audio sequentially. Moreover, we utilize unconditional generation to imp","authors_text":"Ha-Yeong Choi, Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee","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":"2023-07-30T08:49:55Z","title":"HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16171","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":"sha256:95bad5c916b17653e81e54cf569526eba10e7092a46ddef53f1c4e53e706a2db","target":"record","created_at":"2026-07-05T06:35:59Z","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":"38261b51448bdb67a48e4dd30f9190ba7d63601b99bdbf864d14ea7290944622","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":"2023-07-30T08:49:55Z","title_canon_sha256":"9d883b7d55d6cd17d0a1e68b018015fe3a37bb66b43b05da3c54f037c2a76124"},"schema_version":"1.0","source":{"id":"2307.16171","kind":"arxiv","version":1}},"canonical_sha256":"373c97d214d5c6082919a446d4e78165d4c0a276504e1f4ffc97b689767ce593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"373c97d214d5c6082919a446d4e78165d4c0a276504e1f4ffc97b689767ce593","first_computed_at":"2026-07-05T06:35:59.637617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:59.637617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y9cziHe6P1C5qG4azn2byiytXCkiJ+fwXE9ei4Xh0LuY7I3CB1BcgqtL5c9SHUr1cMf+FZLqkuTcbSmfcPpgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:59.638154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95bad5c916b17653e81e54cf569526eba10e7092a46ddef53f1c4e53e706a2db","sha256:e1b62fade34b25204cee2cbfcc63e0a8fe355790d19648324746b58304eaaa4a"],"state_sha256":"17b27eab952cfaab60e2467025161df760f3935ff540e2e89d8f9b7722a6dc1c"}