{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HRXUOKQXRBMESXZITK6LAQBZC7","short_pith_number":"pith:HRXUOKQX","schema_version":"1.0","canonical_sha256":"3c6f472a178858495f289abcb0403917fce2e48a580c5f42d6054932bd3f61e9","source":{"kind":"arxiv","id":"2501.01347","version":4},"attestation_state":"computed","paper":{"title":"AdaptVC: High Quality Voice Conversion with Adaptive Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jaehun Kim, Ji-Hoon Kim, Joon Son Chung, Seongkyu Mun, Tan Dat Nguyen, Yeunju Choi","submitted_at":"2025-01-02T16:54:08Z","abstract_excerpt":"The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to extract disentangled linguistic content from the source and voice style from the reference. While existing approaches leverage various methods to isolate the two, a generalization still requires further attention, especially for robustness in zero-shot scenarios. In this paper, we achieve successful disentanglement of content and speaker features by tuning self-supervised speech features with adapters. The adapters ar"},"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":"2501.01347","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T16:54:08Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"8ea583a240965cf5ee5e854141fb79d65b8742d81efb98fb4b7c75af3d7a19b7","abstract_canon_sha256":"a697ff8e2a1fb00ff43ef7e32a8a7126bccd012961be1f3989aa702b2c6bdc08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:45.724828Z","signature_b64":"PqIIYDvBFzyJ5URUAwKiMUzgnH3vO18a7dqC+kAgn3MRJV2IL/vOi/3uPCtUV5xa5muWuT82an6p+JguKQBpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6f472a178858495f289abcb0403917fce2e48a580c5f42d6054932bd3f61e9","last_reissued_at":"2026-07-05T10:00:45.724289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:45.724289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaptVC: High Quality Voice Conversion with Adaptive Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jaehun Kim, Ji-Hoon Kim, Joon Son Chung, Seongkyu Mun, Tan Dat Nguyen, Yeunju Choi","submitted_at":"2025-01-02T16:54:08Z","abstract_excerpt":"The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to extract disentangled linguistic content from the source and voice style from the reference. While existing approaches leverage various methods to isolate the two, a generalization still requires further attention, especially for robustness in zero-shot scenarios. In this paper, we achieve successful disentanglement of content and speaker features by tuning self-supervised speech features with adapters. The adapters ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01347","kind":"arxiv","version":4},"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/2501.01347/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":"2501.01347","created_at":"2026-07-05T10:00:45.724365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01347v4","created_at":"2026-07-05T10:00:45.724365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01347","created_at":"2026-07-05T10:00:45.724365+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRXUOKQXRBME","created_at":"2026-07-05T10:00:45.724365+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRXUOKQXRBMESXZI","created_at":"2026-07-05T10:00:45.724365+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRXUOKQX","created_at":"2026-07-05T10:00:45.724365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16691","citing_title":"EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7","json":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7.json","graph_json":"https://pith.science/api/pith-number/HRXUOKQXRBMESXZITK6LAQBZC7/graph.json","events_json":"https://pith.science/api/pith-number/HRXUOKQXRBMESXZITK6LAQBZC7/events.json","paper":"https://pith.science/paper/HRXUOKQX"},"agent_actions":{"view_html":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7","download_json":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7.json","view_paper":"https://pith.science/paper/HRXUOKQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01347&json=true","fetch_graph":"https://pith.science/api/pith-number/HRXUOKQXRBMESXZITK6LAQBZC7/graph.json","fetch_events":"https://pith.science/api/pith-number/HRXUOKQXRBMESXZITK6LAQBZC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7/action/storage_attestation","attest_author":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7/action/author_attestation","sign_citation":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7/action/citation_signature","submit_replication":"https://pith.science/pith/HRXUOKQXRBMESXZITK6LAQBZC7/action/replication_record"}},"created_at":"2026-07-05T10:00:45.724365+00:00","updated_at":"2026-07-05T10:00:45.724365+00:00"}