{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5SQNY5HT2NO2Z2DQ7Q2VK6G76B","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":"85dd7d164b661d02ae1b34acfb77fe3678eb1761e8147dd48cd998fefd6a3e1c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-01T17:44:18Z","title_canon_sha256":"e94948fb4dce1a547b1938841d4b7110a3f146761861d943410e89a564033508"},"schema_version":"1.0","source":{"id":"2307.00393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00393","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00393v1","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00393","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_12","alias_value":"5SQNY5HT2NO2","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_16","alias_value":"5SQNY5HT2NO2Z2DQ","created_at":"2026-07-05T06:26:55Z"},{"alias_kind":"pith_short_8","alias_value":"5SQNY5HT","created_at":"2026-07-05T06:26:55Z"}],"graph_snapshots":[{"event_id":"sha256:0117b01c75b8d39ee7c3e2288d89c1d7a073a19f6fbd4a1c40191dcbd90ecfc6","target":"graph","created_at":"2026-07-05T06:26:55Z","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/2307.00393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice conversion systems have made significant advancements in terms of naturalness and similarity in common voice conversion tasks. However, their performance in more complex tasks such as cross-lingual voice conversion and expressive voice conversion remains imperfect. In this study, we propose a novel approach that combines a jointly trained speaker encoder and content features extracted from the cross-lingual speech recognition model Whisper to achieve high-quality cross-lingual voice conversion. Additionally, we introduce a speaker consistency loss to the joint encoder, which improves the","authors_text":"Carlos Toshinori Ishi, Chaoran Liu, Hiroshi Ishiguro, Houjian Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-01T17:44:18Z","title":"Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00393","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":"sha256:978ef32e03d12f5ec3091db70851b90c18c0a9773d02a3b1cd58667495190cbc","target":"record","created_at":"2026-07-05T06:26:55Z","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":"85dd7d164b661d02ae1b34acfb77fe3678eb1761e8147dd48cd998fefd6a3e1c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-01T17:44:18Z","title_canon_sha256":"e94948fb4dce1a547b1938841d4b7110a3f146761861d943410e89a564033508"},"schema_version":"1.0","source":{"id":"2307.00393","kind":"arxiv","version":1}},"canonical_sha256":"eca0dc74f3d35dace870fc355578dff07d142eac14003b318855ef8974248058","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eca0dc74f3d35dace870fc355578dff07d142eac14003b318855ef8974248058","first_computed_at":"2026-07-05T06:26:55.566424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:55.566424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NpnhoqfDJqxIclMANQUZM+fpkyVZpa5CGHRjnW09dUVSWWYGcUnGKJHKj13Ss+HOOo2pb7BhHI5Ue+8Z+LonDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:55.566836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:978ef32e03d12f5ec3091db70851b90c18c0a9773d02a3b1cd58667495190cbc","sha256:0117b01c75b8d39ee7c3e2288d89c1d7a073a19f6fbd4a1c40191dcbd90ecfc6"],"state_sha256":"25f762edd8cc7b258030b4753b13158c0ea918408ed772a858ffcd1658603b1c"}