{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5SQNY5HT2NO2Z2DQ7Q2VK6G76B","short_pith_number":"pith:5SQNY5HT","schema_version":"1.0","canonical_sha256":"eca0dc74f3d35dace870fc355578dff07d142eac14003b318855ef8974248058","source":{"kind":"arxiv","id":"2307.00393","version":1},"attestation_state":"computed","paper":{"title":"Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Carlos Toshinori Ishi, Chaoran Liu, Hiroshi Ishiguro, Houjian Guo","submitted_at":"2023-07-01T17:44:18Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.00393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-01T17:44:18Z","cross_cats_sorted":[],"title_canon_sha256":"e94948fb4dce1a547b1938841d4b7110a3f146761861d943410e89a564033508","abstract_canon_sha256":"85dd7d164b661d02ae1b34acfb77fe3678eb1761e8147dd48cd998fefd6a3e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:55.566836Z","signature_b64":"NpnhoqfDJqxIclMANQUZM+fpkyVZpa5CGHRjnW09dUVSWWYGcUnGKJHKj13Ss+HOOo2pb7BhHI5Ue+8Z+LonDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eca0dc74f3d35dace870fc355578dff07d142eac14003b318855ef8974248058","last_reissued_at":"2026-07-05T06:26:55.566424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:55.566424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Carlos Toshinori Ishi, Chaoran Liu, Hiroshi Ishiguro, Houjian Guo","submitted_at":"2023-07-01T17:44:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00393","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.00393/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.00393","created_at":"2026-07-05T06:26:55.566478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00393v1","created_at":"2026-07-05T06:26:55.566478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00393","created_at":"2026-07-05T06:26:55.566478+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SQNY5HT2NO2","created_at":"2026-07-05T06:26:55.566478+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SQNY5HT2NO2Z2DQ","created_at":"2026-07-05T06:26:55.566478+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SQNY5HT","created_at":"2026-07-05T06:26:55.566478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B","json":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B.json","graph_json":"https://pith.science/api/pith-number/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/graph.json","events_json":"https://pith.science/api/pith-number/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/events.json","paper":"https://pith.science/paper/5SQNY5HT"},"agent_actions":{"view_html":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B","download_json":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B.json","view_paper":"https://pith.science/paper/5SQNY5HT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00393&json=true","fetch_graph":"https://pith.science/api/pith-number/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/graph.json","fetch_events":"https://pith.science/api/pith-number/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/action/storage_attestation","attest_author":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/action/author_attestation","sign_citation":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/action/citation_signature","submit_replication":"https://pith.science/pith/5SQNY5HT2NO2Z2DQ7Q2VK6G76B/action/replication_record"}},"created_at":"2026-07-05T06:26:55.566478+00:00","updated_at":"2026-07-05T06:26:55.566478+00:00"}