{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4DVE7FJW5C5PNIWQTTYFH5DRFA","short_pith_number":"pith:4DVE7FJW","schema_version":"1.0","canonical_sha256":"e0ea4f9536e8baf6a2d09cf053f471280db8f6e37bb6953db2ed9884f68618cf","source":{"kind":"arxiv","id":"2208.08757","version":1},"attestation_state":"computed","paper":{"title":"Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aolan Sun, Haolin Zhuang, Helen Meng, Huaizhen Tang, Jianzong Wang, Jie Wang, Methawee Tantrawenith, Ning Cheng, Sicheng Yang, Xintao Zhao, Zhiyong Wu","submitted_at":"2022-08-18T10:36:27Z","abstract_excerpt":"One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic. Existing works generally disentangle timbre, while information about pitch, rhythm and content is still mixed together. To perform one-shot VC effectively with further disentangling these speech components, we employ random resampling for pitch and content encoder and use the variational contrastive log-ratio upper bound of mutual information and gradient reversal layer based adversarial mutual information learning to ensure the different parts of the latent space containing"},"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":"2208.08757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-08-18T10:36:27Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"794eeca5c1d904b694e794f4d5530a2cd024a98400f4fae1044baeade70cc2ff","abstract_canon_sha256":"3ae30e3295fdc980623de709fd9a814cc70b49495da93722231ab880e5f837f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:02.579189Z","signature_b64":"5Xv9emF1EDEkmjBrFM3NQZIQNHBM3xMGN/QHw6IUp0FzHeojG+52i8PmOeKwE5ucTAEWgYhAJ1ih60iLU0RXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0ea4f9536e8baf6a2d09cf053f471280db8f6e37bb6953db2ed9884f68618cf","last_reissued_at":"2026-07-05T04:51:02.578702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:02.578702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aolan Sun, Haolin Zhuang, Helen Meng, Huaizhen Tang, Jianzong Wang, Jie Wang, Methawee Tantrawenith, Ning Cheng, Sicheng Yang, Xintao Zhao, Zhiyong Wu","submitted_at":"2022-08-18T10:36:27Z","abstract_excerpt":"One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic. Existing works generally disentangle timbre, while information about pitch, rhythm and content is still mixed together. To perform one-shot VC effectively with further disentangling these speech components, we employ random resampling for pitch and content encoder and use the variational contrastive log-ratio upper bound of mutual information and gradient reversal layer based adversarial mutual information learning to ensure the different parts of the latent space containing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08757","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/2208.08757/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":"2208.08757","created_at":"2026-07-05T04:51:02.578773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08757v1","created_at":"2026-07-05T04:51:02.578773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08757","created_at":"2026-07-05T04:51:02.578773+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DVE7FJW5C5P","created_at":"2026-07-05T04:51:02.578773+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DVE7FJW5C5PNIWQ","created_at":"2026-07-05T04:51:02.578773+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DVE7FJW","created_at":"2026-07-05T04:51:02.578773+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/4DVE7FJW5C5PNIWQTTYFH5DRFA","json":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA.json","graph_json":"https://pith.science/api/pith-number/4DVE7FJW5C5PNIWQTTYFH5DRFA/graph.json","events_json":"https://pith.science/api/pith-number/4DVE7FJW5C5PNIWQTTYFH5DRFA/events.json","paper":"https://pith.science/paper/4DVE7FJW"},"agent_actions":{"view_html":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA","download_json":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA.json","view_paper":"https://pith.science/paper/4DVE7FJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08757&json=true","fetch_graph":"https://pith.science/api/pith-number/4DVE7FJW5C5PNIWQTTYFH5DRFA/graph.json","fetch_events":"https://pith.science/api/pith-number/4DVE7FJW5C5PNIWQTTYFH5DRFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA/action/storage_attestation","attest_author":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA/action/author_attestation","sign_citation":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA/action/citation_signature","submit_replication":"https://pith.science/pith/4DVE7FJW5C5PNIWQTTYFH5DRFA/action/replication_record"}},"created_at":"2026-07-05T04:51:02.578773+00:00","updated_at":"2026-07-05T04:51:02.578773+00:00"}