{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IYGZTIXHEYCQ2QXCXH7V2VWDO6","short_pith_number":"pith:IYGZTIXH","schema_version":"1.0","canonical_sha256":"460d99a2e726050d42e2b9ff5d56c377babcb8cc12cf6273a40a80da63d4bbd5","source":{"kind":"arxiv","id":"2311.04693","version":1},"attestation_state":"computed","paper":{"title":"Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2023-11-08T14:02:53Z","abstract_excerpt":"Although voice conversion (VC) systems have shown a remarkable ability to transfer voice style, existing methods still have an inaccurate pitch and low speaker adaptation quality. To address these challenges, we introduce Diff-HierVC, a hierarchical VC system based on two diffusion models. We first introduce DiffPitch, which can effectively generate F0 with the target voice style. Subsequently, the generated F0 is fed to DiffVoice to convert the speech with a target voice style. Furthermore, using the source-filter encoder, we disentangle the speech and use the converted Mel-spectrogram as a d"},"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":"2311.04693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-08T14:02:53Z","cross_cats_sorted":["cs.AI","cs.SD","eess.SP"],"title_canon_sha256":"04aedcf1d514ff20305a96c10e0b783cdec90cab431c21c5a95c7dd071e130f8","abstract_canon_sha256":"e73f924475b779c4af530268233bbd01d3506cdc9cd7dd1088b51999c063ff97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:40.139135Z","signature_b64":"U2TyE0itqeTyMUUPOvHVDVxwAqi2Q84pkiyxbjHmX0UrLSlQgwfSNKPG8INxCCbWYcAC2YSAoUT3b72GofWzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"460d99a2e726050d42e2b9ff5d56c377babcb8cc12cf6273a40a80da63d4bbd5","last_reissued_at":"2026-07-05T07:10:40.138659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:40.138659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2023-11-08T14:02:53Z","abstract_excerpt":"Although voice conversion (VC) systems have shown a remarkable ability to transfer voice style, existing methods still have an inaccurate pitch and low speaker adaptation quality. To address these challenges, we introduce Diff-HierVC, a hierarchical VC system based on two diffusion models. We first introduce DiffPitch, which can effectively generate F0 with the target voice style. Subsequently, the generated F0 is fed to DiffVoice to convert the speech with a target voice style. Furthermore, using the source-filter encoder, we disentangle the speech and use the converted Mel-spectrogram as a d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04693","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/2311.04693/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":"2311.04693","created_at":"2026-07-05T07:10:40.138717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04693v1","created_at":"2026-07-05T07:10:40.138717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04693","created_at":"2026-07-05T07:10:40.138717+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYGZTIXHEYCQ","created_at":"2026-07-05T07:10:40.138717+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYGZTIXHEYCQ2QXC","created_at":"2026-07-05T07:10:40.138717+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYGZTIXH","created_at":"2026-07-05T07:10:40.138717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6","json":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6.json","graph_json":"https://pith.science/api/pith-number/IYGZTIXHEYCQ2QXCXH7V2VWDO6/graph.json","events_json":"https://pith.science/api/pith-number/IYGZTIXHEYCQ2QXCXH7V2VWDO6/events.json","paper":"https://pith.science/paper/IYGZTIXH"},"agent_actions":{"view_html":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6","download_json":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6.json","view_paper":"https://pith.science/paper/IYGZTIXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04693&json=true","fetch_graph":"https://pith.science/api/pith-number/IYGZTIXHEYCQ2QXCXH7V2VWDO6/graph.json","fetch_events":"https://pith.science/api/pith-number/IYGZTIXHEYCQ2QXCXH7V2VWDO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6/action/storage_attestation","attest_author":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6/action/author_attestation","sign_citation":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6/action/citation_signature","submit_replication":"https://pith.science/pith/IYGZTIXHEYCQ2QXCXH7V2VWDO6/action/replication_record"}},"created_at":"2026-07-05T07:10:40.138717+00:00","updated_at":"2026-07-05T07:10:40.138717+00:00"}