{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PMCCYVBRGCXZWDZFGBU3PMB3RR","short_pith_number":"pith:PMCCYVBR","schema_version":"1.0","canonical_sha256":"7b042c543130af9b0f253069b7b03b8c6d33a74d86615636e6a4e34831b53e6e","source":{"kind":"arxiv","id":"2106.00992","version":1},"attestation_state":"computed","paper":{"title":"NVC-Net: End-to-End Adversarial Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bac Nguyen, Fabien Cardinaux","submitted_at":"2021-06-02T07:19:58Z","abstract_excerpt":"Voice conversion has gained increasing popularity in many applications of speech synthesis. The idea is to change the voice identity from one speaker into another while keeping the linguistic content unchanged. Many voice conversion approaches rely on the use of a vocoder to reconstruct the speech from acoustic features, and as a consequence, the speech quality heavily depends on such a vocoder. In this paper, we propose NVC-Net, an end-to-end adversarial network, which performs voice conversion directly on the raw audio waveform of arbitrary length. By disentangling the speaker identity from "},"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":"2106.00992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-02T07:19:58Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"da55cd0d59bd6bc2ca45f9dadcbb05a789253bec8d34970db058b29a3c10acdb","abstract_canon_sha256":"72d811f08d92894bc23fd83fb16c6cf79c7e65be742317f1468d16d4a65260e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:42.604303Z","signature_b64":"Qnc0cqQnZaIRw+hpvbAoCEyZawLQdedGh9UpALrOFY33NW4ntddSSYNCmTqlupeuWGPv1Z6TGkaTwZDukDRmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b042c543130af9b0f253069b7b03b8c6d33a74d86615636e6a4e34831b53e6e","last_reissued_at":"2026-07-05T02:45:42.603879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:42.603879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NVC-Net: End-to-End Adversarial Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bac Nguyen, Fabien Cardinaux","submitted_at":"2021-06-02T07:19:58Z","abstract_excerpt":"Voice conversion has gained increasing popularity in many applications of speech synthesis. The idea is to change the voice identity from one speaker into another while keeping the linguistic content unchanged. Many voice conversion approaches rely on the use of a vocoder to reconstruct the speech from acoustic features, and as a consequence, the speech quality heavily depends on such a vocoder. In this paper, we propose NVC-Net, an end-to-end adversarial network, which performs voice conversion directly on the raw audio waveform of arbitrary length. By disentangling the speaker identity from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00992","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/2106.00992/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":"2106.00992","created_at":"2026-07-05T02:45:42.603944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00992v1","created_at":"2026-07-05T02:45:42.603944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00992","created_at":"2026-07-05T02:45:42.603944+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMCCYVBRGCXZ","created_at":"2026-07-05T02:45:42.603944+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMCCYVBRGCXZWDZF","created_at":"2026-07-05T02:45:42.603944+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMCCYVBR","created_at":"2026-07-05T02:45:42.603944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR","json":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR.json","graph_json":"https://pith.science/api/pith-number/PMCCYVBRGCXZWDZFGBU3PMB3RR/graph.json","events_json":"https://pith.science/api/pith-number/PMCCYVBRGCXZWDZFGBU3PMB3RR/events.json","paper":"https://pith.science/paper/PMCCYVBR"},"agent_actions":{"view_html":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR","download_json":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR.json","view_paper":"https://pith.science/paper/PMCCYVBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00992&json=true","fetch_graph":"https://pith.science/api/pith-number/PMCCYVBRGCXZWDZFGBU3PMB3RR/graph.json","fetch_events":"https://pith.science/api/pith-number/PMCCYVBRGCXZWDZFGBU3PMB3RR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR/action/storage_attestation","attest_author":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR/action/author_attestation","sign_citation":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR/action/citation_signature","submit_replication":"https://pith.science/pith/PMCCYVBRGCXZWDZFGBU3PMB3RR/action/replication_record"}},"created_at":"2026-07-05T02:45:42.603944+00:00","updated_at":"2026-07-05T02:45:42.603944+00:00"}