{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LKE3LTIJRRW24WKTLM6IXKUZF3","short_pith_number":"pith:LKE3LTIJ","schema_version":"1.0","canonical_sha256":"5a89b5cd098c6dae59535b3c8baa992ec212245555cc2049da747fe0e6fbe7b1","source":{"kind":"arxiv","id":"2107.10394","version":2},"attestation_state":"computed","paper":{"title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ali Zare, Nima Mesgarani, Yinghao Aaron Li","submitted_at":"2021-07-21T23:44:17Z","abstract_excerpt":"We present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model significantly outperforms previous VC models. Although our model is trained only with 20 English speakers, it generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion. Using a style encoder, our framework can also convert plain reading speech into stylistic speech, such as emotional and falsetto speech. Subjec"},"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":"2107.10394","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-07-21T23:44:17Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ed4e0097e4775fc54f0c310b69f4a98ed4acf60e5ff67a32a45e8997ff6796c2","abstract_canon_sha256":"f6a7f892d3f03128a61c40876bb6d32ababee47e80a5749145783d17a4142b38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:10.689812Z","signature_b64":"p5jayM9PESKeixduxjTvlARbExute+rrjw7VR6pWliXso1U2T2H7Ya2Wkik4gJAqgKP9OJLtRzs5UoICvXJRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a89b5cd098c6dae59535b3c8baa992ec212245555cc2049da747fe0e6fbe7b1","last_reissued_at":"2026-07-05T03:00:10.689280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:10.689280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ali Zare, Nima Mesgarani, Yinghao Aaron Li","submitted_at":"2021-07-21T23:44:17Z","abstract_excerpt":"We present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model significantly outperforms previous VC models. Although our model is trained only with 20 English speakers, it generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion. Using a style encoder, our framework can also convert plain reading speech into stylistic speech, such as emotional and falsetto speech. Subjec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10394","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/2107.10394/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":"2107.10394","created_at":"2026-07-05T03:00:10.689356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10394v2","created_at":"2026-07-05T03:00:10.689356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10394","created_at":"2026-07-05T03:00:10.689356+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKE3LTIJRRW2","created_at":"2026-07-05T03:00:10.689356+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKE3LTIJRRW24WKT","created_at":"2026-07-05T03:00:10.689356+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKE3LTIJ","created_at":"2026-07-05T03:00:10.689356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08184","citing_title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13229","citing_title":"ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3","json":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3.json","graph_json":"https://pith.science/api/pith-number/LKE3LTIJRRW24WKTLM6IXKUZF3/graph.json","events_json":"https://pith.science/api/pith-number/LKE3LTIJRRW24WKTLM6IXKUZF3/events.json","paper":"https://pith.science/paper/LKE3LTIJ"},"agent_actions":{"view_html":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3","download_json":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3.json","view_paper":"https://pith.science/paper/LKE3LTIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10394&json=true","fetch_graph":"https://pith.science/api/pith-number/LKE3LTIJRRW24WKTLM6IXKUZF3/graph.json","fetch_events":"https://pith.science/api/pith-number/LKE3LTIJRRW24WKTLM6IXKUZF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3/action/storage_attestation","attest_author":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3/action/author_attestation","sign_citation":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3/action/citation_signature","submit_replication":"https://pith.science/pith/LKE3LTIJRRW24WKTLM6IXKUZF3/action/replication_record"}},"created_at":"2026-07-05T03:00:10.689356+00:00","updated_at":"2026-07-05T03:00:10.689356+00:00"}