{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T6PMUTJDGR6F555ZAGR3OFVT3A","short_pith_number":"pith:T6PMUTJD","schema_version":"1.0","canonical_sha256":"9f9eca4d23347c5ef7b901a3b716b3d82311214b1b9ecc1f561e90d92f5e85ab","source":{"kind":"arxiv","id":"2404.15637","version":2},"attestation_state":"computed","paper":{"title":"HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Charles Patrick Martin, Jing Zhang, Xinlei Niu","submitted_at":"2024-04-24T04:18:31Z","abstract_excerpt":"We introduce HybridVC, a voice conversion (VC) framework built upon a pre-trained conditional variational autoencoder (CVAE) that combines the strengths of a latent model with contrastive learning. HybridVC supports text and audio prompts, enabling more flexible voice style conversion. HybridVC models a latent distribution conditioned on speaker embeddings acquired by a pretrained speaker encoder and optimises style text embeddings to align with the speaker style information through contrastive learning in parallel. Therefore, HybridVC can be efficiently trained under limited computational res"},"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":"2404.15637","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-24T04:18:31Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"53e10341c27fc4abd1fd72de1085fe8c39339833eaef0a49ba455f528af2b6d6","abstract_canon_sha256":"2562c872997ccff9f5a8ecba5d38b62c1bf3feb1f100028c13fc8a6ff775d64e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:25.748416Z","signature_b64":"bjKxZjfMISA/W2rDgHTkYHPqRfjMrnf8YvBkaJKP3iqgbeaL/DmdmlAR7hanGMgWOUfoSfs4il3x+GijZEhAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9eca4d23347c5ef7b901a3b716b3d82311214b1b9ecc1f561e90d92f5e85ab","last_reissued_at":"2026-07-05T09:11:25.747995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:25.747995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Charles Patrick Martin, Jing Zhang, Xinlei Niu","submitted_at":"2024-04-24T04:18:31Z","abstract_excerpt":"We introduce HybridVC, a voice conversion (VC) framework built upon a pre-trained conditional variational autoencoder (CVAE) that combines the strengths of a latent model with contrastive learning. HybridVC supports text and audio prompts, enabling more flexible voice style conversion. HybridVC models a latent distribution conditioned on speaker embeddings acquired by a pretrained speaker encoder and optimises style text embeddings to align with the speaker style information through contrastive learning in parallel. Therefore, HybridVC can be efficiently trained under limited computational res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15637","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/2404.15637/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":"2404.15637","created_at":"2026-07-05T09:11:25.748048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15637v2","created_at":"2026-07-05T09:11:25.748048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15637","created_at":"2026-07-05T09:11:25.748048+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6PMUTJDGR6F","created_at":"2026-07-05T09:11:25.748048+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6PMUTJDGR6F555Z","created_at":"2026-07-05T09:11:25.748048+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6PMUTJD","created_at":"2026-07-05T09:11:25.748048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23435","citing_title":"AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A","json":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A.json","graph_json":"https://pith.science/api/pith-number/T6PMUTJDGR6F555ZAGR3OFVT3A/graph.json","events_json":"https://pith.science/api/pith-number/T6PMUTJDGR6F555ZAGR3OFVT3A/events.json","paper":"https://pith.science/paper/T6PMUTJD"},"agent_actions":{"view_html":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A","download_json":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A.json","view_paper":"https://pith.science/paper/T6PMUTJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15637&json=true","fetch_graph":"https://pith.science/api/pith-number/T6PMUTJDGR6F555ZAGR3OFVT3A/graph.json","fetch_events":"https://pith.science/api/pith-number/T6PMUTJDGR6F555ZAGR3OFVT3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A/action/storage_attestation","attest_author":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A/action/author_attestation","sign_citation":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A/action/citation_signature","submit_replication":"https://pith.science/pith/T6PMUTJDGR6F555ZAGR3OFVT3A/action/replication_record"}},"created_at":"2026-07-05T09:11:25.748048+00:00","updated_at":"2026-07-05T09:11:25.748048+00:00"}