{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NNRLUJFLB656EVWOHMNWCWW6TU","short_pith_number":"pith:NNRLUJFL","schema_version":"1.0","canonical_sha256":"6b62ba24ab0fbbe256ce3b1b615ade9d31cb65d0ee846afe5df5a644baeb6a71","source":{"kind":"arxiv","id":"1802.06006","version":3},"attestation_state":"computed","paper":{"title":"Neural Voice Cloning with a Few Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jitong Chen, Kainan Peng, Sercan O. Arik, Wei Ping, Yanqi Zhou","submitted_at":"2018-02-14T18:24:41Z","abstract_excerpt":"Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice cloning system that takes a few audio samples as input. We study two approaches: speaker adaptation and speaker encoding. Speaker adaptation is based on fine-tuning a multi-speaker generative model with a few cloning samples. Speaker encoding is based on training a separate model to directly infer a new speaker embedding from cloning audios and to be used with"},"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":"1802.06006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T18:24:41Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"46939201e85e36a800d0749bef428abe96a5ca1fedde6d461c1fac1c39a01e99","abstract_canon_sha256":"a2782133c617d411c0ea5bcc0df9b15a888cf8e389e2a0a2014da4923d5e46db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:32.179524Z","signature_b64":"FFJG8lOBYHE35M+TyvWgcOdfWSu1ttb5hU6ewbZQsZ7I4quFlfw9b/rQZGYjRmrplj7f1xJyzSf2M2fNK6fsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b62ba24ab0fbbe256ce3b1b615ade9d31cb65d0ee846afe5df5a644baeb6a71","last_reissued_at":"2026-05-18T00:03:32.178910Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:32.178910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Voice Cloning with a Few Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jitong Chen, Kainan Peng, Sercan O. Arik, Wei Ping, Yanqi Zhou","submitted_at":"2018-02-14T18:24:41Z","abstract_excerpt":"Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice cloning system that takes a few audio samples as input. We study two approaches: speaker adaptation and speaker encoding. Speaker adaptation is based on fine-tuning a multi-speaker generative model with a few cloning samples. Speaker encoding is based on training a separate model to directly infer a new speaker embedding from cloning audios and to be used with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06006","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.06006","created_at":"2026-05-18T00:03:32.178989+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06006v3","created_at":"2026-05-18T00:03:32.178989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06006","created_at":"2026-05-18T00:03:32.178989+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNRLUJFLB656","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNRLUJFLB656EVWO","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNRLUJFL","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU","json":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU.json","graph_json":"https://pith.science/api/pith-number/NNRLUJFLB656EVWOHMNWCWW6TU/graph.json","events_json":"https://pith.science/api/pith-number/NNRLUJFLB656EVWOHMNWCWW6TU/events.json","paper":"https://pith.science/paper/NNRLUJFL"},"agent_actions":{"view_html":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU","download_json":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU.json","view_paper":"https://pith.science/paper/NNRLUJFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06006&json=true","fetch_graph":"https://pith.science/api/pith-number/NNRLUJFLB656EVWOHMNWCWW6TU/graph.json","fetch_events":"https://pith.science/api/pith-number/NNRLUJFLB656EVWOHMNWCWW6TU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU/action/storage_attestation","attest_author":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU/action/author_attestation","sign_citation":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU/action/citation_signature","submit_replication":"https://pith.science/pith/NNRLUJFLB656EVWOHMNWCWW6TU/action/replication_record"}},"created_at":"2026-05-18T00:03:32.178989+00:00","updated_at":"2026-05-18T00:03:32.178989+00:00"}