{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UZFRQH7NP6WLR743PYNPCBUJX7","short_pith_number":"pith:UZFRQH7N","schema_version":"1.0","canonical_sha256":"a64b181fed7facb8ff9b7e1af10689bfceab875f298f9259e9ec91e8629b408f","source":{"kind":"arxiv","id":"2111.12277","version":2},"attestation_state":"computed","paper":{"title":"One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hongqiang Du, Lei Xie, Mengxiao Bi, Pengcheng Zhu, Qicong Xie, Tao Li, Zhichao Wang","submitted_at":"2021-11-24T05:30:47Z","abstract_excerpt":"One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one u"},"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":"2111.12277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-11-24T05:30:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ab0bbebe2d130d3fc3347711f33473a56fde9c06d87039cac18c95772031e701","abstract_canon_sha256":"f2ebf8d709249587099cbbbb881e3f64469e4413d962dcdd8153adc79ba46364"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:35.646978Z","signature_b64":"izCQhWY2K2C1k4reo9DXuqEnHArm6RuzA76jUyO3McTO5KE/WACg82J8SCrYhfXWtORuEYepz/Q89ClPLX7oBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a64b181fed7facb8ff9b7e1af10689bfceab875f298f9259e9ec91e8629b408f","last_reissued_at":"2026-07-05T03:58:35.646565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:35.646565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hongqiang Du, Lei Xie, Mengxiao Bi, Pengcheng Zhu, Qicong Xie, Tao Li, Zhichao Wang","submitted_at":"2021-11-24T05:30:47Z","abstract_excerpt":"One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12277","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/2111.12277/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":"2111.12277","created_at":"2026-07-05T03:58:35.646622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12277v2","created_at":"2026-07-05T03:58:35.646622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12277","created_at":"2026-07-05T03:58:35.646622+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZFRQH7NP6WL","created_at":"2026-07-05T03:58:35.646622+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZFRQH7NP6WLR743","created_at":"2026-07-05T03:58:35.646622+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZFRQH7N","created_at":"2026-07-05T03:58:35.646622+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/UZFRQH7NP6WLR743PYNPCBUJX7","json":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7.json","graph_json":"https://pith.science/api/pith-number/UZFRQH7NP6WLR743PYNPCBUJX7/graph.json","events_json":"https://pith.science/api/pith-number/UZFRQH7NP6WLR743PYNPCBUJX7/events.json","paper":"https://pith.science/paper/UZFRQH7N"},"agent_actions":{"view_html":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7","download_json":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7.json","view_paper":"https://pith.science/paper/UZFRQH7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12277&json=true","fetch_graph":"https://pith.science/api/pith-number/UZFRQH7NP6WLR743PYNPCBUJX7/graph.json","fetch_events":"https://pith.science/api/pith-number/UZFRQH7NP6WLR743PYNPCBUJX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7/action/storage_attestation","attest_author":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7/action/author_attestation","sign_citation":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7/action/citation_signature","submit_replication":"https://pith.science/pith/UZFRQH7NP6WLR743PYNPCBUJX7/action/replication_record"}},"created_at":"2026-07-05T03:58:35.646622+00:00","updated_at":"2026-07-05T03:58:35.646622+00:00"}