{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H244IRE43HEV6RIRWQRM7KUKZP","short_pith_number":"pith:H244IRE4","schema_version":"1.0","canonical_sha256":"3eb9c4449cd9c95f4511b422cfaa8acbef6d2e12061e090b2e38cc1bd5c3d83a","source":{"kind":"arxiv","id":"2310.04004","version":1},"attestation_state":"computed","paper":{"title":"U-Style: Cascading U-nets with Multi-level Speaker and Style Modeling for Zero-Shot Voice Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jian Cong, Lei Xie, Qiao Tian, Tao Li, Xinfa Zhu, Yuping Wang, Zhichao Wang","submitted_at":"2023-10-06T04:24:41Z","abstract_excerpt":"Zero-shot speaker cloning aims to synthesize speech for any target speaker unseen during TTS system building, given only a single speech reference of the speaker at hand. Although more practical in real applications, the current zero-shot methods still produce speech with undesirable naturalness and speaker similarity. Moreover, endowing the target speaker with arbitrary speaking styles in the zero-shot setup has not been considered. This is because the unique challenge of zero-shot speaker and style cloning is to learn the disentangled speaker and style representations from only short referen"},"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":"2310.04004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-06T04:24:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3a36665add009aae16c6a957869433732a71c2bc81176e9356d1271e171ec5e3","abstract_canon_sha256":"1a0a9459d831675237020c98ea63f8173f41e6e5509ec37331fea17fc29a4ff3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:56.583111Z","signature_b64":"jqt84sP6mCW/nlLJrnaTVBTGUB1+Laa1kd01ICW1u4iIvsnHK/gk5q5Bah6s+j1oyZ1PWlZgV55+P9UBDietDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eb9c4449cd9c95f4511b422cfaa8acbef6d2e12061e090b2e38cc1bd5c3d83a","last_reissued_at":"2026-07-05T06:57:56.582710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:56.582710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U-Style: Cascading U-nets with Multi-level Speaker and Style Modeling for Zero-Shot Voice Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jian Cong, Lei Xie, Qiao Tian, Tao Li, Xinfa Zhu, Yuping Wang, Zhichao Wang","submitted_at":"2023-10-06T04:24:41Z","abstract_excerpt":"Zero-shot speaker cloning aims to synthesize speech for any target speaker unseen during TTS system building, given only a single speech reference of the speaker at hand. Although more practical in real applications, the current zero-shot methods still produce speech with undesirable naturalness and speaker similarity. Moreover, endowing the target speaker with arbitrary speaking styles in the zero-shot setup has not been considered. This is because the unique challenge of zero-shot speaker and style cloning is to learn the disentangled speaker and style representations from only short referen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04004","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/2310.04004/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":"2310.04004","created_at":"2026-07-05T06:57:56.582772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04004v1","created_at":"2026-07-05T06:57:56.582772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04004","created_at":"2026-07-05T06:57:56.582772+00:00"},{"alias_kind":"pith_short_12","alias_value":"H244IRE43HEV","created_at":"2026-07-05T06:57:56.582772+00:00"},{"alias_kind":"pith_short_16","alias_value":"H244IRE43HEV6RIR","created_at":"2026-07-05T06:57:56.582772+00:00"},{"alias_kind":"pith_short_8","alias_value":"H244IRE4","created_at":"2026-07-05T06:57:56.582772+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/H244IRE43HEV6RIRWQRM7KUKZP","json":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP.json","graph_json":"https://pith.science/api/pith-number/H244IRE43HEV6RIRWQRM7KUKZP/graph.json","events_json":"https://pith.science/api/pith-number/H244IRE43HEV6RIRWQRM7KUKZP/events.json","paper":"https://pith.science/paper/H244IRE4"},"agent_actions":{"view_html":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP","download_json":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP.json","view_paper":"https://pith.science/paper/H244IRE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04004&json=true","fetch_graph":"https://pith.science/api/pith-number/H244IRE43HEV6RIRWQRM7KUKZP/graph.json","fetch_events":"https://pith.science/api/pith-number/H244IRE43HEV6RIRWQRM7KUKZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP/action/storage_attestation","attest_author":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP/action/author_attestation","sign_citation":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP/action/citation_signature","submit_replication":"https://pith.science/pith/H244IRE43HEV6RIRWQRM7KUKZP/action/replication_record"}},"created_at":"2026-07-05T06:57:56.582772+00:00","updated_at":"2026-07-05T06:57:56.582772+00:00"}