{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5546DJN6N4F3JEKZ3FPHFE6327","short_pith_number":"pith:5546DJN6","schema_version":"1.0","canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","source":{"kind":"arxiv","id":"2309.03364","version":1},"attestation_state":"computed","paper":{"title":"Highly Controllable Diffusion-based Any-to-Any Voice Conversion Model with Frame-level Prosody Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erik Visser, Kyungguen Byun, Sunkuk Moon","submitted_at":"2023-09-06T21:16:58Z","abstract_excerpt":"We propose a highly controllable voice manipulation system that can perform any-to-any voice conversion (VC) and prosody modulation simultaneously. State-of-the-art VC systems can transfer sentence-level characteristics such as speaker, emotion, and speaking style. However, manipulating the frame-level prosody, such as pitch, energy and speaking rate, still remains challenging. Our proposed model utilizes a frame-level prosody feature to effectively transfer such properties. Specifically, pitch and energy trajectories are integrated in a prosody conditioning module and then fed alongside speak"},"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":"2309.03364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-06T21:16:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0e8091be23202a242a8f84b6e33dc0eabc18cc1c11f6d9402e1fc5c1a68fd5e0","abstract_canon_sha256":"2194a23987edd577b66d8d8f18e8fc9e1b7e783eaae1a5681b7e75d39c998526"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:27.020920Z","signature_b64":"3s7m7jcG3cTw2cprXs3zafGSVkrPQw0rRrEyQ0xcUwvef+szJoXYMKvTppzJRVhhD7jf5aUOGsxs2P92cbPGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","last_reissued_at":"2026-07-05T06:48:27.020447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:27.020447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Highly Controllable Diffusion-based Any-to-Any Voice Conversion Model with Frame-level Prosody Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erik Visser, Kyungguen Byun, Sunkuk Moon","submitted_at":"2023-09-06T21:16:58Z","abstract_excerpt":"We propose a highly controllable voice manipulation system that can perform any-to-any voice conversion (VC) and prosody modulation simultaneously. State-of-the-art VC systems can transfer sentence-level characteristics such as speaker, emotion, and speaking style. However, manipulating the frame-level prosody, such as pitch, energy and speaking rate, still remains challenging. Our proposed model utilizes a frame-level prosody feature to effectively transfer such properties. Specifically, pitch and energy trajectories are integrated in a prosody conditioning module and then fed alongside speak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03364","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/2309.03364/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":"2309.03364","created_at":"2026-07-05T06:48:27.020510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03364v1","created_at":"2026-07-05T06:48:27.020510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03364","created_at":"2026-07-05T06:48:27.020510+00:00"},{"alias_kind":"pith_short_12","alias_value":"5546DJN6N4F3","created_at":"2026-07-05T06:48:27.020510+00:00"},{"alias_kind":"pith_short_16","alias_value":"5546DJN6N4F3JEKZ","created_at":"2026-07-05T06:48:27.020510+00:00"},{"alias_kind":"pith_short_8","alias_value":"5546DJN6","created_at":"2026-07-05T06:48:27.020510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04817","citing_title":"Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327","json":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327.json","graph_json":"https://pith.science/api/pith-number/5546DJN6N4F3JEKZ3FPHFE6327/graph.json","events_json":"https://pith.science/api/pith-number/5546DJN6N4F3JEKZ3FPHFE6327/events.json","paper":"https://pith.science/paper/5546DJN6"},"agent_actions":{"view_html":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327","download_json":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327.json","view_paper":"https://pith.science/paper/5546DJN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03364&json=true","fetch_graph":"https://pith.science/api/pith-number/5546DJN6N4F3JEKZ3FPHFE6327/graph.json","fetch_events":"https://pith.science/api/pith-number/5546DJN6N4F3JEKZ3FPHFE6327/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/action/storage_attestation","attest_author":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/action/author_attestation","sign_citation":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/action/citation_signature","submit_replication":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/action/replication_record"}},"created_at":"2026-07-05T06:48:27.020510+00:00","updated_at":"2026-07-05T06:48:27.020510+00:00"}