{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K4TK7HPYACSQOOQEPUZRKX7HSH","short_pith_number":"pith:K4TK7HPY","schema_version":"1.0","canonical_sha256":"5726af9df800a5073a047d33155fe791d17251a1f3b82ed026a62e8fd3920999","source":{"kind":"arxiv","id":"2406.09844","version":1},"attestation_state":"computed","paper":{"title":"Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongbin Zhou, Lei Xie, Linhan Ma, Wendi He, Xinfa Zhu, Yuanjun Lv, Zhichao Wang, Ziqian Wang","submitted_at":"2024-06-14T08:51:31Z","abstract_excerpt":"Zero-shot voice conversion (VC) aims to transform source speech into arbitrary unseen target voice while keeping the linguistic content unchanged. Recent VC methods have made significant progress, but semantic losses in the decoupling process as well as training-inference mismatch still hinder conversion performance. In this paper, we propose Vec-Tok-VC+, a novel prompt-based zero-shot VC model improved from Vec-Tok Codec, achieving voice conversion given only a 3s target speaker prompt. We design a residual-enhanced K-Means decoupler to enhance the semantic content extraction with a two-layer"},"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":"2406.09844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T08:51:31Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e6e577b52460cbf9159486997bec47940a5a19186d581eb5b824efcb778776a7","abstract_canon_sha256":"0038f0e38aa8db9f6a193873449802f469f4e67a20211a5b3ca7f154bbd15436"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:00.867925Z","signature_b64":"mbl+mSxNWQA4+YLLQZG+gQCmTg9GKsDkkFCC5TBK8mbopXNJqtLuIXtmodHcDEVFGH26RDf3v3HtEMZ5Jn97Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5726af9df800a5073a047d33155fe791d17251a1f3b82ed026a62e8fd3920999","last_reissued_at":"2026-07-05T08:32:00.867284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:00.867284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongbin Zhou, Lei Xie, Linhan Ma, Wendi He, Xinfa Zhu, Yuanjun Lv, Zhichao Wang, Ziqian Wang","submitted_at":"2024-06-14T08:51:31Z","abstract_excerpt":"Zero-shot voice conversion (VC) aims to transform source speech into arbitrary unseen target voice while keeping the linguistic content unchanged. Recent VC methods have made significant progress, but semantic losses in the decoupling process as well as training-inference mismatch still hinder conversion performance. In this paper, we propose Vec-Tok-VC+, a novel prompt-based zero-shot VC model improved from Vec-Tok Codec, achieving voice conversion given only a 3s target speaker prompt. We design a residual-enhanced K-Means decoupler to enhance the semantic content extraction with a two-layer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09844","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/2406.09844/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":"2406.09844","created_at":"2026-07-05T08:32:00.867360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09844v1","created_at":"2026-07-05T08:32:00.867360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09844","created_at":"2026-07-05T08:32:00.867360+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4TK7HPYACSQ","created_at":"2026-07-05T08:32:00.867360+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4TK7HPYACSQOOQE","created_at":"2026-07-05T08:32:00.867360+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4TK7HPY","created_at":"2026-07-05T08:32:00.867360+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/K4TK7HPYACSQOOQEPUZRKX7HSH","json":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH.json","graph_json":"https://pith.science/api/pith-number/K4TK7HPYACSQOOQEPUZRKX7HSH/graph.json","events_json":"https://pith.science/api/pith-number/K4TK7HPYACSQOOQEPUZRKX7HSH/events.json","paper":"https://pith.science/paper/K4TK7HPY"},"agent_actions":{"view_html":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH","download_json":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH.json","view_paper":"https://pith.science/paper/K4TK7HPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09844&json=true","fetch_graph":"https://pith.science/api/pith-number/K4TK7HPYACSQOOQEPUZRKX7HSH/graph.json","fetch_events":"https://pith.science/api/pith-number/K4TK7HPYACSQOOQEPUZRKX7HSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH/action/storage_attestation","attest_author":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH/action/author_attestation","sign_citation":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH/action/citation_signature","submit_replication":"https://pith.science/pith/K4TK7HPYACSQOOQEPUZRKX7HSH/action/replication_record"}},"created_at":"2026-07-05T08:32:00.867360+00:00","updated_at":"2026-07-05T08:32:00.867360+00:00"}