{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FSOVZJFY33BVXOJSTDLZAQETBI","short_pith_number":"pith:FSOVZJFY","schema_version":"1.0","canonical_sha256":"2c9d5ca4b8dec35bb93298d79040930a16abac557b3fee0d0339fd1435a6de15","source":{"kind":"arxiv","id":"2007.12932","version":2},"attestation_state":"computed","paper":{"title":"Non-parallel Emotion Conversion using a Deep-Generative Hybrid Network and an Adversarial Pair Discriminator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Archana Venkataraman, Jacob Sager, Ravi Shankar","submitted_at":"2020-07-25T13:50:00Z","abstract_excerpt":"We introduce a novel method for emotion conversion in speech that does not require parallel training data. Our approach loosely relies on a cycle-GAN schema to minimize the reconstruction error from converting back and forth between emotion pairs. However, unlike the conventional cycle-GAN, our discriminator classifies whether a pair of input real and generated samples corresponds to the desired emotion conversion (e.g., A to B) or to its inverse (B to A). We will show that this setup, which we refer to as a variational cycle-GAN (VC-GAN), is equivalent to minimizing the empirical KL divergenc"},"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":"2007.12932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-25T13:50:00Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"3b3cf914ccb1cf2e834c087065e267311370a33974e3f72be9ae9ad59a3a37d7","abstract_canon_sha256":"c7ee2d4750ba59e311060cadb97da4817f39c8bcf4b24ffa7544ad6e4f658e53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:22.396311Z","signature_b64":"TwShwzoDM9NA0whlo2eMbzmm7azvTvLcJVoEkB7XiZ+drFm0GUKgo+Me2PH12dKwJiXiCfNULUdQcDZwVRxVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c9d5ca4b8dec35bb93298d79040930a16abac557b3fee0d0339fd1435a6de15","last_reissued_at":"2026-07-05T01:26:22.395811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:22.395811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-parallel Emotion Conversion using a Deep-Generative Hybrid Network and an Adversarial Pair Discriminator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Archana Venkataraman, Jacob Sager, Ravi Shankar","submitted_at":"2020-07-25T13:50:00Z","abstract_excerpt":"We introduce a novel method for emotion conversion in speech that does not require parallel training data. Our approach loosely relies on a cycle-GAN schema to minimize the reconstruction error from converting back and forth between emotion pairs. However, unlike the conventional cycle-GAN, our discriminator classifies whether a pair of input real and generated samples corresponds to the desired emotion conversion (e.g., A to B) or to its inverse (B to A). We will show that this setup, which we refer to as a variational cycle-GAN (VC-GAN), is equivalent to minimizing the empirical KL divergenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12932","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/2007.12932/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":"2007.12932","created_at":"2026-07-05T01:26:22.395871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12932v2","created_at":"2026-07-05T01:26:22.395871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12932","created_at":"2026-07-05T01:26:22.395871+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSOVZJFY33BV","created_at":"2026-07-05T01:26:22.395871+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSOVZJFY33BVXOJS","created_at":"2026-07-05T01:26:22.395871+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSOVZJFY","created_at":"2026-07-05T01:26:22.395871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13805","citing_title":"ClapFM-EVC: High-Fidelity and Flexible Emotional Voice Conversion with Dual Control from Natural Language and Speech","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI","json":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI.json","graph_json":"https://pith.science/api/pith-number/FSOVZJFY33BVXOJSTDLZAQETBI/graph.json","events_json":"https://pith.science/api/pith-number/FSOVZJFY33BVXOJSTDLZAQETBI/events.json","paper":"https://pith.science/paper/FSOVZJFY"},"agent_actions":{"view_html":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI","download_json":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI.json","view_paper":"https://pith.science/paper/FSOVZJFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12932&json=true","fetch_graph":"https://pith.science/api/pith-number/FSOVZJFY33BVXOJSTDLZAQETBI/graph.json","fetch_events":"https://pith.science/api/pith-number/FSOVZJFY33BVXOJSTDLZAQETBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI/action/storage_attestation","attest_author":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI/action/author_attestation","sign_citation":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI/action/citation_signature","submit_replication":"https://pith.science/pith/FSOVZJFY33BVXOJSTDLZAQETBI/action/replication_record"}},"created_at":"2026-07-05T01:26:22.395871+00:00","updated_at":"2026-07-05T01:26:22.395871+00:00"}