{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EBZVRM5WGJ6WM4WXJQFB4XAGBC","short_pith_number":"pith:EBZVRM5W","schema_version":"1.0","canonical_sha256":"207358b3b6327d6672d74c0a1e5c0608a89470239eb87c3c569d88fa475b9b05","source":{"kind":"arxiv","id":"2203.09708","version":1},"attestation_state":"computed","paper":{"title":"Improve few-shot voice cloning using multi-modal learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haitong Zhang, Yue Lin","submitted_at":"2022-03-18T02:57:32Z","abstract_excerpt":"Recently, few-shot voice cloning has achieved a significant improvement. However, most models for few-shot voice cloning are single-modal, and multi-modal few-shot voice cloning has been understudied. In this paper, we propose to use multi-modal learning to improve the few-shot voice cloning performance. Inspired by the recent works on unsupervised speech representation, the proposed multi-modal system is built by extending Tacotron2 with an unsupervised speech representation module. We evaluate our proposed system in two few-shot voice cloning scenarios, namely few-shot text-to-speech(TTS) an"},"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":"2203.09708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-18T02:57:32Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"84733c6e09932fb2832117b95cf7cb38d605a705b1b950a1de50c62eec012770","abstract_canon_sha256":"0441ac0c74e70e103afdf657f2fe3652a748e84e0dfacf8c672a062d33e7535a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:22.684257Z","signature_b64":"bgZXVShUR+MahYxJFGf7TAj10NjzT46yV5SjgwGuHmKHG7bEMFw6Fsfd3QadPZH/AYzZoDfV4/7SiKa8WkLyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"207358b3b6327d6672d74c0a1e5c0608a89470239eb87c3c569d88fa475b9b05","last_reissued_at":"2026-07-05T04:06:22.683849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:22.683849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improve few-shot voice cloning using multi-modal learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haitong Zhang, Yue Lin","submitted_at":"2022-03-18T02:57:32Z","abstract_excerpt":"Recently, few-shot voice cloning has achieved a significant improvement. However, most models for few-shot voice cloning are single-modal, and multi-modal few-shot voice cloning has been understudied. In this paper, we propose to use multi-modal learning to improve the few-shot voice cloning performance. Inspired by the recent works on unsupervised speech representation, the proposed multi-modal system is built by extending Tacotron2 with an unsupervised speech representation module. We evaluate our proposed system in two few-shot voice cloning scenarios, namely few-shot text-to-speech(TTS) an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09708","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/2203.09708/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":"2203.09708","created_at":"2026-07-05T04:06:22.683904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09708v1","created_at":"2026-07-05T04:06:22.683904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09708","created_at":"2026-07-05T04:06:22.683904+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBZVRM5WGJ6W","created_at":"2026-07-05T04:06:22.683904+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBZVRM5WGJ6WM4WX","created_at":"2026-07-05T04:06:22.683904+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBZVRM5W","created_at":"2026-07-05T04:06:22.683904+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/EBZVRM5WGJ6WM4WXJQFB4XAGBC","json":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC.json","graph_json":"https://pith.science/api/pith-number/EBZVRM5WGJ6WM4WXJQFB4XAGBC/graph.json","events_json":"https://pith.science/api/pith-number/EBZVRM5WGJ6WM4WXJQFB4XAGBC/events.json","paper":"https://pith.science/paper/EBZVRM5W"},"agent_actions":{"view_html":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC","download_json":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC.json","view_paper":"https://pith.science/paper/EBZVRM5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09708&json=true","fetch_graph":"https://pith.science/api/pith-number/EBZVRM5WGJ6WM4WXJQFB4XAGBC/graph.json","fetch_events":"https://pith.science/api/pith-number/EBZVRM5WGJ6WM4WXJQFB4XAGBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC/action/storage_attestation","attest_author":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC/action/author_attestation","sign_citation":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC/action/citation_signature","submit_replication":"https://pith.science/pith/EBZVRM5WGJ6WM4WXJQFB4XAGBC/action/replication_record"}},"created_at":"2026-07-05T04:06:22.683904+00:00","updated_at":"2026-07-05T04:06:22.683904+00:00"}