{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X6L6GXXPVHTLTHIPRF4KMCYTGQ","short_pith_number":"pith:X6L6GXXP","schema_version":"1.0","canonical_sha256":"bf97e35eefa9e6b99d0f8978a60b13342a12c1e103508fc5765872f203138344","source":{"kind":"arxiv","id":"2309.07586","version":1},"attestation_state":"computed","paper":{"title":"Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Arnab Das, Ingo Siegert, Sebastian Stober, Suhita Ghosh, Tim Polzehl, Yamini Sinha","submitted_at":"2023-09-14T10:40:43Z","abstract_excerpt":"Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content. However, emotion preservation is crucial for natural human-computer interaction. The well-known voice conversion technique StarGANv2-VC achieves anonymisation but fails to preserve emotion. This work presents an any-to-many semi-supervised StarGANv2-VC variant trained on partially emotion-labelled non-parallel data. We propose emotion-aware losses computed on the emotion embeddings and acoustic features correlated to emotion. Additionally, we use an emotion clas"},"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":"2309.07586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T10:40:43Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3523fae0173efae22752f8e532ceddb02bc7cd4b89cc6904d3b68cab41745cab","abstract_canon_sha256":"85a46245e454848f6d16c663f91611c6ee99fcc6ba42d2342929527b97bc3299"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:45.248829Z","signature_b64":"WgibYFMRERZImvXNjVeVKVMEVf96C21gvNJyVEQOIx10JgOaJI/w2ij3YE73Z4EgNGL76L3F5eLXOwkLkPxjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf97e35eefa9e6b99d0f8978a60b13342a12c1e103508fc5765872f203138344","last_reissued_at":"2026-07-05T06:50:45.248339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:45.248339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Arnab Das, Ingo Siegert, Sebastian Stober, Suhita Ghosh, Tim Polzehl, Yamini Sinha","submitted_at":"2023-09-14T10:40:43Z","abstract_excerpt":"Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content. However, emotion preservation is crucial for natural human-computer interaction. The well-known voice conversion technique StarGANv2-VC achieves anonymisation but fails to preserve emotion. This work presents an any-to-many semi-supervised StarGANv2-VC variant trained on partially emotion-labelled non-parallel data. We propose emotion-aware losses computed on the emotion embeddings and acoustic features correlated to emotion. Additionally, we use an emotion clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07586","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/2309.07586/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":"2309.07586","created_at":"2026-07-05T06:50:45.248401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07586v1","created_at":"2026-07-05T06:50:45.248401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07586","created_at":"2026-07-05T06:50:45.248401+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6L6GXXPVHTL","created_at":"2026-07-05T06:50:45.248401+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6L6GXXPVHTLTHIP","created_at":"2026-07-05T06:50:45.248401+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6L6GXXP","created_at":"2026-07-05T06:50:45.248401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15313","citing_title":"DDPO-VC: Speaker De-Identification via Diffusion Denoising Policy Optimization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ","json":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ.json","graph_json":"https://pith.science/api/pith-number/X6L6GXXPVHTLTHIPRF4KMCYTGQ/graph.json","events_json":"https://pith.science/api/pith-number/X6L6GXXPVHTLTHIPRF4KMCYTGQ/events.json","paper":"https://pith.science/paper/X6L6GXXP"},"agent_actions":{"view_html":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ","download_json":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ.json","view_paper":"https://pith.science/paper/X6L6GXXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07586&json=true","fetch_graph":"https://pith.science/api/pith-number/X6L6GXXPVHTLTHIPRF4KMCYTGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/X6L6GXXPVHTLTHIPRF4KMCYTGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ/action/storage_attestation","attest_author":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ/action/author_attestation","sign_citation":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ/action/citation_signature","submit_replication":"https://pith.science/pith/X6L6GXXPVHTLTHIPRF4KMCYTGQ/action/replication_record"}},"created_at":"2026-07-05T06:50:45.248401+00:00","updated_at":"2026-07-05T06:50:45.248401+00:00"}