{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YUBTNXOF3ZUR44JG6HX7JR4DQ2","short_pith_number":"pith:YUBTNXOF","schema_version":"1.0","canonical_sha256":"c50336ddc5de691e7126f1eff4c783868268cd38594c5dc477df2d25381fcf5f","source":{"kind":"arxiv","id":"2505.24336","version":1},"attestation_state":"computed","paper":{"title":"When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Choonghyeon Lee, Minsu Kang, Namhyun Cho, Seolhee Lee","submitted_at":"2025-05-30T08:24:41Z","abstract_excerpt":"Human to non-human voice conversion (H2NH-VC) transforms human speech into animal or designed vocalizations. Unlike prior studies focused on dog-sounds and 16 or 22.05kHz audio transformation, this work addresses a broader range of non-speech sounds, including natural sounds (lion-roars, birdsongs) and designed voice (synthetic growls). To accomodate generation of diverse non-speech sounds and 44.1kHz high-quality audio transformation, we introduce a preprocessing pipeline and an improved CVAE-based H2NH-VC model, both optimized for human and non-human voices. Experimental results showed that "},"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":"2505.24336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T08:24:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.SP"],"title_canon_sha256":"743b787211cd65f4a690486adec7e12289447ca93a8a7f8b1b344c940497d94e","abstract_canon_sha256":"002721b8df155a6fc96851982d1e3569418eff3b4ef6e5b1ddca70569402fc59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:47.027714Z","signature_b64":"K+bKNCUqNPZbsP/zn0N0JSmyn74vhUbBzhcKZTcNN50TIaE5gxFyPMCovO0nhUJ6EEMfwXN8SPx/QYoGix78Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50336ddc5de691e7126f1eff4c783868268cd38594c5dc477df2d25381fcf5f","last_reissued_at":"2026-07-05T11:12:47.027267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:47.027267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Choonghyeon Lee, Minsu Kang, Namhyun Cho, Seolhee Lee","submitted_at":"2025-05-30T08:24:41Z","abstract_excerpt":"Human to non-human voice conversion (H2NH-VC) transforms human speech into animal or designed vocalizations. Unlike prior studies focused on dog-sounds and 16 or 22.05kHz audio transformation, this work addresses a broader range of non-speech sounds, including natural sounds (lion-roars, birdsongs) and designed voice (synthetic growls). To accomodate generation of diverse non-speech sounds and 44.1kHz high-quality audio transformation, we introduce a preprocessing pipeline and an improved CVAE-based H2NH-VC model, both optimized for human and non-human voices. Experimental results showed that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24336","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/2505.24336/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":"2505.24336","created_at":"2026-07-05T11:12:47.027337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24336v1","created_at":"2026-07-05T11:12:47.027337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24336","created_at":"2026-07-05T11:12:47.027337+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUBTNXOF3ZUR","created_at":"2026-07-05T11:12:47.027337+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUBTNXOF3ZUR44JG","created_at":"2026-07-05T11:12:47.027337+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUBTNXOF","created_at":"2026-07-05T11:12:47.027337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24336","citing_title":"When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2","json":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2.json","graph_json":"https://pith.science/api/pith-number/YUBTNXOF3ZUR44JG6HX7JR4DQ2/graph.json","events_json":"https://pith.science/api/pith-number/YUBTNXOF3ZUR44JG6HX7JR4DQ2/events.json","paper":"https://pith.science/paper/YUBTNXOF"},"agent_actions":{"view_html":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2","download_json":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2.json","view_paper":"https://pith.science/paper/YUBTNXOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24336&json=true","fetch_graph":"https://pith.science/api/pith-number/YUBTNXOF3ZUR44JG6HX7JR4DQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/YUBTNXOF3ZUR44JG6HX7JR4DQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2/action/storage_attestation","attest_author":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2/action/author_attestation","sign_citation":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2/action/citation_signature","submit_replication":"https://pith.science/pith/YUBTNXOF3ZUR44JG6HX7JR4DQ2/action/replication_record"}},"created_at":"2026-07-05T11:12:47.027337+00:00","updated_at":"2026-07-05T11:12:47.027337+00:00"}