{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5QMOSKSMUQJ5PTZDNULOGH3BSH","short_pith_number":"pith:5QMOSKSM","schema_version":"1.0","canonical_sha256":"ec18e92a4ca413d7cf236d16e31f6191d08e883ebd7c7e570837b698c8cb6637","source":{"kind":"arxiv","id":"2110.03347","version":2},"attestation_state":"computed","paper":{"title":"Cloning one's voice using very limited data in the wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongyang Dai, Li Chen, Lu Liu, Ming Tu, Qiao Tian, Rui Xia, Yuanzhe Chen, Yuping Wang, Yuxuan Wang","submitted_at":"2021-10-07T11:40:08Z","abstract_excerpt":"With the increasing popularity of speech synthesis products, the industry has put forward more requirements for personalized speech synthesis: (1) How to use low-resource, easily accessible data to clone a person's voice. (2) How to clone a person's voice while controlling the style and prosody. To solve the above two problems, we proposed the Hieratron model framework in which the prosody and timbre are modeled separately using two modules, therefore, the independent control of timbre and the other characteristics of audio can be achieved while generating speech. The practice shows that, for "},"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":"2110.03347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T11:40:08Z","cross_cats_sorted":["cs.HC","cs.SD"],"title_canon_sha256":"1fcf78cb58ef40d43891722d31c5798cac34dc82a6f720480904fd9f341830b8","abstract_canon_sha256":"aeed2c771dfa28b67abb8421a9c9edce16993aee72edf47297e3f8a9beb4f6ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:57.681567Z","signature_b64":"pgJn+fxh+/A8o1AUhdEEjOopvpTGrNyX817BBZOWim62lVNIEUmAursKgRDs2sZ84YCjjFNCfLGYsWCrr7GvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec18e92a4ca413d7cf236d16e31f6191d08e883ebd7c7e570837b698c8cb6637","last_reissued_at":"2026-07-05T03:20:57.681153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:57.681153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cloning one's voice using very limited data in the wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongyang Dai, Li Chen, Lu Liu, Ming Tu, Qiao Tian, Rui Xia, Yuanzhe Chen, Yuping Wang, Yuxuan Wang","submitted_at":"2021-10-07T11:40:08Z","abstract_excerpt":"With the increasing popularity of speech synthesis products, the industry has put forward more requirements for personalized speech synthesis: (1) How to use low-resource, easily accessible data to clone a person's voice. (2) How to clone a person's voice while controlling the style and prosody. To solve the above two problems, we proposed the Hieratron model framework in which the prosody and timbre are modeled separately using two modules, therefore, the independent control of timbre and the other characteristics of audio can be achieved while generating speech. The practice shows that, for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03347","kind":"arxiv","version":2},"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/2110.03347/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":"2110.03347","created_at":"2026-07-05T03:20:57.681214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03347v2","created_at":"2026-07-05T03:20:57.681214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03347","created_at":"2026-07-05T03:20:57.681214+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QMOSKSMUQJ5","created_at":"2026-07-05T03:20:57.681214+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QMOSKSMUQJ5PTZD","created_at":"2026-07-05T03:20:57.681214+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QMOSKSM","created_at":"2026-07-05T03:20:57.681214+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/5QMOSKSMUQJ5PTZDNULOGH3BSH","json":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH.json","graph_json":"https://pith.science/api/pith-number/5QMOSKSMUQJ5PTZDNULOGH3BSH/graph.json","events_json":"https://pith.science/api/pith-number/5QMOSKSMUQJ5PTZDNULOGH3BSH/events.json","paper":"https://pith.science/paper/5QMOSKSM"},"agent_actions":{"view_html":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH","download_json":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH.json","view_paper":"https://pith.science/paper/5QMOSKSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03347&json=true","fetch_graph":"https://pith.science/api/pith-number/5QMOSKSMUQJ5PTZDNULOGH3BSH/graph.json","fetch_events":"https://pith.science/api/pith-number/5QMOSKSMUQJ5PTZDNULOGH3BSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH/action/storage_attestation","attest_author":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH/action/author_attestation","sign_citation":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH/action/citation_signature","submit_replication":"https://pith.science/pith/5QMOSKSMUQJ5PTZDNULOGH3BSH/action/replication_record"}},"created_at":"2026-07-05T03:20:57.681214+00:00","updated_at":"2026-07-05T03:20:57.681214+00:00"}