{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6IJTL75ZMZISQWG5NJDMNFDY5H","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":"1450cf84eff72c32e15bc9e570c92eed7b6dd0b3e2e2852622e8398d0009204c","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-08T07:24:03Z","title_canon_sha256":"7465da3cc18e1810686b8b9b76a5a2d1e7391d6a5703ff528d691af16c74f831"},"schema_version":"1.0","source":{"id":"2409.05004","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05004","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05004v2","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05004","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"6IJTL75ZMZIS","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"6IJTL75ZMZISQWG5","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"6IJTL75Z","created_at":"2026-07-05T09:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:caa20f1639c7fa138863af67c0d2ff10bc36eebd83479f26701955386c7f2db5","target":"graph","created_at":"2026-07-05T09:05:19Z","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/2409.05004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic","authors_text":"Junichi Yamagishi, Mingyang Zhang, Shuai Wang, Xuechen Liu, Yanmin Qian, Zhengyang Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-08T07:24:03Z","title":"Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05004","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":"sha256:6e72650c6729824ce712fed962e8a4cf0191db07dd3a4d94c6c6755eab5e3df2","target":"record","created_at":"2026-07-05T09:05:19Z","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":"1450cf84eff72c32e15bc9e570c92eed7b6dd0b3e2e2852622e8398d0009204c","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-08T07:24:03Z","title_canon_sha256":"7465da3cc18e1810686b8b9b76a5a2d1e7391d6a5703ff528d691af16c74f831"},"schema_version":"1.0","source":{"id":"2409.05004","kind":"arxiv","version":2}},"canonical_sha256":"f21335ffb966512858dd6a46c69478e9e2e2c9d52289311e2248a42dbd62b190","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f21335ffb966512858dd6a46c69478e9e2e2c9d52289311e2248a42dbd62b190","first_computed_at":"2026-07-05T09:05:19.484290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:19.484290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cSXlaJxzAobv6NoNw/JXbVI5QR1mCrGC7lEHiZG4+S4zJcSgW1ysIATVeybifafFFQBYVAJGeBfro/13xy6lDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:19.484814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05004","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e72650c6729824ce712fed962e8a4cf0191db07dd3a4d94c6c6755eab5e3df2","sha256:caa20f1639c7fa138863af67c0d2ff10bc36eebd83479f26701955386c7f2db5"],"state_sha256":"dc0b1c94cd12340ff2610677a806a864d07390424da41cfa937921baf00cb090"}