{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YYFJ6H3YECL2O4WWPKPSNZ63OX","short_pith_number":"pith:YYFJ6H3Y","schema_version":"1.0","canonical_sha256":"c60a9f1f782097a772d67a9f26e7db75edb36a23d86c8cc54ca2d842ffddae3f","source":{"kind":"arxiv","id":"2302.08296","version":4},"attestation_state":"computed","paper":{"title":"QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Carlos Toshinori Ishi, Chaoran Liu, Hiroshi Ishiguro, Houjian Guo","submitted_at":"2023-02-16T13:49:09Z","abstract_excerpt":"With the development of automatic speech recognition (ASR) and text-to-speech (TTS) technology, high-quality voice conversion (VC) can be achieved by extracting source content information and target speaker information to reconstruct waveforms. However, current methods still require improvement in terms of inference speed. In this study, we propose a lightweight VITS-based VC model that uses the HuBERT-Soft model to extract content information features without speaker information. Through subjective and objective experiments on synthesized speech, the proposed model demonstrates competitive re"},"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":"2302.08296","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-16T13:49:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d2e40b99a5c22f7c53ccc3d99bcc5c34e1f9b5b8d1bf5801f9aaac26e8e67a3d","abstract_canon_sha256":"deb9144d58291ddb17ebe9c54119beeaa635c6f939f14c9c0d704d808a687435"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:52.867998Z","signature_b64":"GU5yitJqbDmaUf+Gj9AdUS7BAr7CoEjohvTG+82FUbLX+goL5iSklSQsmol92QLiWHrPtuLqRAMbGFBYBu9pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c60a9f1f782097a772d67a9f26e7db75edb36a23d86c8cc54ca2d842ffddae3f","last_reissued_at":"2026-07-05T05:44:52.867480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:52.867480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Carlos Toshinori Ishi, Chaoran Liu, Hiroshi Ishiguro, Houjian Guo","submitted_at":"2023-02-16T13:49:09Z","abstract_excerpt":"With the development of automatic speech recognition (ASR) and text-to-speech (TTS) technology, high-quality voice conversion (VC) can be achieved by extracting source content information and target speaker information to reconstruct waveforms. However, current methods still require improvement in terms of inference speed. In this study, we propose a lightweight VITS-based VC model that uses the HuBERT-Soft model to extract content information features without speaker information. Through subjective and objective experiments on synthesized speech, the proposed model demonstrates competitive re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08296","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/2302.08296/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":"2302.08296","created_at":"2026-07-05T05:44:52.867539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08296v4","created_at":"2026-07-05T05:44:52.867539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08296","created_at":"2026-07-05T05:44:52.867539+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYFJ6H3YECL2","created_at":"2026-07-05T05:44:52.867539+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYFJ6H3YECL2O4WW","created_at":"2026-07-05T05:44:52.867539+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYFJ6H3Y","created_at":"2026-07-05T05:44:52.867539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14534","citing_title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX","json":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX.json","graph_json":"https://pith.science/api/pith-number/YYFJ6H3YECL2O4WWPKPSNZ63OX/graph.json","events_json":"https://pith.science/api/pith-number/YYFJ6H3YECL2O4WWPKPSNZ63OX/events.json","paper":"https://pith.science/paper/YYFJ6H3Y"},"agent_actions":{"view_html":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX","download_json":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX.json","view_paper":"https://pith.science/paper/YYFJ6H3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08296&json=true","fetch_graph":"https://pith.science/api/pith-number/YYFJ6H3YECL2O4WWPKPSNZ63OX/graph.json","fetch_events":"https://pith.science/api/pith-number/YYFJ6H3YECL2O4WWPKPSNZ63OX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX/action/storage_attestation","attest_author":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX/action/author_attestation","sign_citation":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX/action/citation_signature","submit_replication":"https://pith.science/pith/YYFJ6H3YECL2O4WWPKPSNZ63OX/action/replication_record"}},"created_at":"2026-07-05T05:44:52.867539+00:00","updated_at":"2026-07-05T05:44:52.867539+00:00"}