{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F62JMV7WUPXRXULQRUHA3J3NNZ","short_pith_number":"pith:F62JMV7W","schema_version":"1.0","canonical_sha256":"2fb49657f6a3ef1bd1708d0e0da76d6e5f7d9723c63c03803e51cf796039eb89","source":{"kind":"arxiv","id":"2102.05630","version":1},"attestation_state":"computed","paper":{"title":"Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Enrico Zovato, Giuseppe Ruggiero, Luigi Di Caro, Vincent Pollet","submitted_at":"2021-02-10T18:43:56Z","abstract_excerpt":"Deep learning models are becoming predominant in many fields of machine learning. Text-to-Speech (TTS), the process of synthesizing artificial speech from text, is no exception. To this end, a deep neural network is usually trained using a corpus of several hours of recorded speech from a single speaker. Trying to produce the voice of a speaker other than the one learned is expensive and requires large effort since it is necessary to record a new dataset and retrain the model. This is the main reason why the TTS models are usually single speaker. The proposed approach has the goal to overcome "},"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":"2102.05630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-02-10T18:43:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c8ab39697f4effb6604f191b9126ba2ffff874698e2e94665cc339225cde7a1a","abstract_canon_sha256":"069b06507b2af8716959f7ae5320dab0e5c587f1a07b264155ba31c4924f5aa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:20.416843Z","signature_b64":"pGuD2p+NO5bnETl1Oi/rqzWjI02H669H/hwgP2stnWGk310ShKlnYc3BpS2FEIbP+eFtHDIsAA5WCn+O1/XgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb49657f6a3ef1bd1708d0e0da76d6e5f7d9723c63c03803e51cf796039eb89","last_reissued_at":"2026-07-05T02:14:20.416345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:20.416345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Enrico Zovato, Giuseppe Ruggiero, Luigi Di Caro, Vincent Pollet","submitted_at":"2021-02-10T18:43:56Z","abstract_excerpt":"Deep learning models are becoming predominant in many fields of machine learning. Text-to-Speech (TTS), the process of synthesizing artificial speech from text, is no exception. To this end, a deep neural network is usually trained using a corpus of several hours of recorded speech from a single speaker. Trying to produce the voice of a speaker other than the one learned is expensive and requires large effort since it is necessary to record a new dataset and retrain the model. This is the main reason why the TTS models are usually single speaker. The proposed approach has the goal to overcome "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05630","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/2102.05630/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":"2102.05630","created_at":"2026-07-05T02:14:20.416410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05630v1","created_at":"2026-07-05T02:14:20.416410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05630","created_at":"2026-07-05T02:14:20.416410+00:00"},{"alias_kind":"pith_short_12","alias_value":"F62JMV7WUPXR","created_at":"2026-07-05T02:14:20.416410+00:00"},{"alias_kind":"pith_short_16","alias_value":"F62JMV7WUPXRXULQ","created_at":"2026-07-05T02:14:20.416410+00:00"},{"alias_kind":"pith_short_8","alias_value":"F62JMV7W","created_at":"2026-07-05T02:14:20.416410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06393","citing_title":"Talking to an AI Mirror: Designing Self-Clone Chatbots for Enhanced Engagement in Digital Mental Health Support","ref_index":106,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ","json":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ.json","graph_json":"https://pith.science/api/pith-number/F62JMV7WUPXRXULQRUHA3J3NNZ/graph.json","events_json":"https://pith.science/api/pith-number/F62JMV7WUPXRXULQRUHA3J3NNZ/events.json","paper":"https://pith.science/paper/F62JMV7W"},"agent_actions":{"view_html":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ","download_json":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ.json","view_paper":"https://pith.science/paper/F62JMV7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05630&json=true","fetch_graph":"https://pith.science/api/pith-number/F62JMV7WUPXRXULQRUHA3J3NNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/F62JMV7WUPXRXULQRUHA3J3NNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ/action/storage_attestation","attest_author":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ/action/author_attestation","sign_citation":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ/action/citation_signature","submit_replication":"https://pith.science/pith/F62JMV7WUPXRXULQRUHA3J3NNZ/action/replication_record"}},"created_at":"2026-07-05T02:14:20.416410+00:00","updated_at":"2026-07-05T02:14:20.416410+00:00"}