{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H4HGTMHU7XCLME3V5YDQORPMPR","short_pith_number":"pith:H4HGTMHU","schema_version":"1.0","canonical_sha256":"3f0e69b0f4fdc4b61375ee070745ec7c5ed40f8a8495159f7f268fb627e81471","source":{"kind":"arxiv","id":"2407.07728","version":5},"attestation_state":"computed","paper":{"title":"SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kejun Zhang, Le Ma, Xin Pan, Yongsheng Feng, Yuhang Jin, Zihao Wang","submitted_at":"2024-07-10T15:00:08Z","abstract_excerpt":"Singing voice conversion (SVC) aims to convert a singer's voice to another singer's from a reference audio while keeping the original semantics. However, existing SVC methods can hardly perform zero-shot due to incomplete feature disentanglement or dependence on the speaker look-up table. We propose the first open-source high-quality zero-shot SVC model SaMoye that can convert singing to human and non-human timbre. SaMoye disentangles the singing voice's features into content, timbre, and pitch features, where we combine multiple ASR models and compress the content features to reduce timbre le"},"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":"2407.07728","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T15:00:08Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"915fef58e2b91ee9d590c36bb38e1aae53de7ae7da33ade71e3bf3261f1e6fb2","abstract_canon_sha256":"e3e19ed40d3081b34d5f63dd62253b8a7bcfc1f295d2da7b9409b44d253bc2e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:50.337916Z","signature_b64":"bCm1K/fgioJ3ABcNA8SOwKyMHupOeahf4RlSfty5GiqBkKCtp/SnAwyE5fYsX0xDQH+O7duwEQlCLHXGdL1PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0e69b0f4fdc4b61375ee070745ec7c5ed40f8a8495159f7f268fb627e81471","last_reissued_at":"2026-07-05T09:35:50.337412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:50.337412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kejun Zhang, Le Ma, Xin Pan, Yongsheng Feng, Yuhang Jin, Zihao Wang","submitted_at":"2024-07-10T15:00:08Z","abstract_excerpt":"Singing voice conversion (SVC) aims to convert a singer's voice to another singer's from a reference audio while keeping the original semantics. However, existing SVC methods can hardly perform zero-shot due to incomplete feature disentanglement or dependence on the speaker look-up table. We propose the first open-source high-quality zero-shot SVC model SaMoye that can convert singing to human and non-human timbre. SaMoye disentangles the singing voice's features into content, timbre, and pitch features, where we combine multiple ASR models and compress the content features to reduce timbre le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07728","kind":"arxiv","version":5},"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/2407.07728/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":"2407.07728","created_at":"2026-07-05T09:35:50.337475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07728v5","created_at":"2026-07-05T09:35:50.337475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07728","created_at":"2026-07-05T09:35:50.337475+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4HGTMHU7XCL","created_at":"2026-07-05T09:35:50.337475+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4HGTMHU7XCLME3V","created_at":"2026-07-05T09:35:50.337475+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4HGTMHU","created_at":"2026-07-05T09:35:50.337475+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/H4HGTMHU7XCLME3V5YDQORPMPR","json":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR.json","graph_json":"https://pith.science/api/pith-number/H4HGTMHU7XCLME3V5YDQORPMPR/graph.json","events_json":"https://pith.science/api/pith-number/H4HGTMHU7XCLME3V5YDQORPMPR/events.json","paper":"https://pith.science/paper/H4HGTMHU"},"agent_actions":{"view_html":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR","download_json":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR.json","view_paper":"https://pith.science/paper/H4HGTMHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07728&json=true","fetch_graph":"https://pith.science/api/pith-number/H4HGTMHU7XCLME3V5YDQORPMPR/graph.json","fetch_events":"https://pith.science/api/pith-number/H4HGTMHU7XCLME3V5YDQORPMPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR/action/storage_attestation","attest_author":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR/action/author_attestation","sign_citation":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR/action/citation_signature","submit_replication":"https://pith.science/pith/H4HGTMHU7XCLME3V5YDQORPMPR/action/replication_record"}},"created_at":"2026-07-05T09:35:50.337475+00:00","updated_at":"2026-07-05T09:35:50.337475+00:00"}