{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GKWFWUWKQ42ESIUVE7E7BZLLNW","short_pith_number":"pith:GKWFWUWK","schema_version":"1.0","canonical_sha256":"32ac5b52ca873449229527c9f0e56b6db44d45f9e3c977b3b0e89967ebb05078","source":{"kind":"arxiv","id":"2103.09420","version":1},"attestation_state":"computed","paper":{"title":"Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Lawrence Carin, Pengyu Cheng, Ruiyi Zhang, Siyang Yuan, Weituo Hao, Zhe Gan","submitted_at":"2021-03-17T03:21:32Z","abstract_excerpt":"Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input "},"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":"2103.09420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-17T03:21:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"35ea7426d59b08020ea6e3366bb8b6d1b229d233d603a84588f336fcfaf63632","abstract_canon_sha256":"a818dd332d1e34a7da49d6e35944db58e2102512b26f71392f30b97f42816276"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:03.519500Z","signature_b64":"Y7Yj+oK48mX8/T7IylqBbFPFwUKhTWQ18emZFo4pO4DNH3j2uugDTXQVPYAhqHmKSnj6ftT7Ng5k7eCIdDdmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32ac5b52ca873449229527c9f0e56b6db44d45f9e3c977b3b0e89967ebb05078","last_reissued_at":"2026-07-05T02:24:03.519065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:03.519065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Lawrence Carin, Pengyu Cheng, Ruiyi Zhang, Siyang Yuan, Weituo Hao, Zhe Gan","submitted_at":"2021-03-17T03:21:32Z","abstract_excerpt":"Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09420","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/2103.09420/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":"2103.09420","created_at":"2026-07-05T02:24:03.519123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09420v1","created_at":"2026-07-05T02:24:03.519123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09420","created_at":"2026-07-05T02:24:03.519123+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKWFWUWKQ42E","created_at":"2026-07-05T02:24:03.519123+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKWFWUWKQ42ESIUV","created_at":"2026-07-05T02:24:03.519123+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKWFWUWK","created_at":"2026-07-05T02:24:03.519123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16530","citing_title":"Learning Text Styles: A Study on Transfer, Attribution, and Verification","ref_index":189,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW","json":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW.json","graph_json":"https://pith.science/api/pith-number/GKWFWUWKQ42ESIUVE7E7BZLLNW/graph.json","events_json":"https://pith.science/api/pith-number/GKWFWUWKQ42ESIUVE7E7BZLLNW/events.json","paper":"https://pith.science/paper/GKWFWUWK"},"agent_actions":{"view_html":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW","download_json":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW.json","view_paper":"https://pith.science/paper/GKWFWUWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09420&json=true","fetch_graph":"https://pith.science/api/pith-number/GKWFWUWKQ42ESIUVE7E7BZLLNW/graph.json","fetch_events":"https://pith.science/api/pith-number/GKWFWUWKQ42ESIUVE7E7BZLLNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW/action/storage_attestation","attest_author":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW/action/author_attestation","sign_citation":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW/action/citation_signature","submit_replication":"https://pith.science/pith/GKWFWUWKQ42ESIUVE7E7BZLLNW/action/replication_record"}},"created_at":"2026-07-05T02:24:03.519123+00:00","updated_at":"2026-07-05T02:24:03.519123+00:00"}