{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OPY2CLDWUN2UO7ZSMIF4W7CJBZ","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":"d66231b953c528230b9ee4dfda6045eb7abfd2e37e7063afdd7ef4f6e306afea","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-12T02:36:04Z","title_canon_sha256":"928ab0ae4540d8688aca08a170f03dcc1559b277458fd4799c432551d184b142"},"schema_version":"1.0","source":{"id":"2305.07204","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07204","created_at":"2026-07-05T08:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07204v3","created_at":"2026-07-05T08:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07204","created_at":"2026-07-05T08:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"OPY2CLDWUN2U","created_at":"2026-07-05T08:20:22Z"},{"alias_kind":"pith_short_16","alias_value":"OPY2CLDWUN2UO7ZS","created_at":"2026-07-05T08:20:22Z"},{"alias_kind":"pith_short_8","alias_value":"OPY2CLDW","created_at":"2026-07-05T08:20:22Z"}],"graph_snapshots":[{"event_id":"sha256:a61c3059d07ec78ba15b75e66741125d14ac50063b0971d831ac3e16cbfd765c","target":"graph","created_at":"2026-07-05T08:20:22Z","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/2305.07204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot voice conversion (VC) converts source speech into the voice of any desired speaker using only one utterance of the speaker without requiring additional model updates. Typical methods use a speaker representation from a pre-trained speaker verification (SV) model or learn speaker representation during VC training to achieve zero-shot VC. However, existing speaker modeling methods overlook the variation of speaker information richness in temporal and frequency channel dimensions of speech. This insufficient speaker modeling hampers the ability of the VC model to accurately represent un","authors_text":"Lei Xie, Liumeng Xue, Qiao Tian, Qiuqiang Kong, Yuanzhe Chen, Yuping Wang, Zhichao Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-12T02:36:04Z","title":"Multi-level Temporal-channel Speaker Retrieval for Zero-shot Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07204","kind":"arxiv","version":3},"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:d051cc3a6a394ef257a16a44c73a81156e02a7e66a29d023cbdb9d27f24e032e","target":"record","created_at":"2026-07-05T08:20:22Z","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":"d66231b953c528230b9ee4dfda6045eb7abfd2e37e7063afdd7ef4f6e306afea","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-12T02:36:04Z","title_canon_sha256":"928ab0ae4540d8688aca08a170f03dcc1559b277458fd4799c432551d184b142"},"schema_version":"1.0","source":{"id":"2305.07204","kind":"arxiv","version":3}},"canonical_sha256":"73f1a12c76a375477f32620bcb7c490e615db66bcb31e3cc042655f6978f66d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f1a12c76a375477f32620bcb7c490e615db66bcb31e3cc042655f6978f66d6","first_computed_at":"2026-07-05T08:20:22.722505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:22.722505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2WfOs8nCa8YPsPUxhhTyOJEWfbonb9ZUc+eHqRyv0fUSrykXHyzQ+4ADEMq9gv2OwY7ta1VTsOAnSAgOM6jzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:22.722978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07204","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d051cc3a6a394ef257a16a44c73a81156e02a7e66a29d023cbdb9d27f24e032e","sha256:a61c3059d07ec78ba15b75e66741125d14ac50063b0971d831ac3e16cbfd765c"],"state_sha256":"4d15aa7502b1483490d6f9773a8c5340dc8bdab5b69254cc6abd072b6f6e2120"}