{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BM5UYCLNXRHKC553CZ2CRN7ZXW","short_pith_number":"pith:BM5UYCLN","schema_version":"1.0","canonical_sha256":"0b3b4c096dbc4ea177bb167428b7f9bd8377e986e29425f213c726959686966f","source":{"kind":"arxiv","id":"2208.04035","version":1},"attestation_state":"computed","paper":{"title":"TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Edward Xiao, Huaizhen Tang, Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Zhen Zeng","submitted_at":"2022-08-08T10:33:36Z","abstract_excerpt":"Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity and the speech content using information-constraining bottlenecks. However, due to the pure autoencoder training method, it is difficult to evaluate the separation effect of content and speaker identity. In this paper, a novel voice conversion framework, named $\\boldsymbol T$ext $\\boldsymbol G$uided $\\boldsymbol A$utoVC(TGAVC), is proposed to more effectivel"},"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":"2208.04035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-08T10:33:36Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"b6b2e105b51b184da50f76397830faf859266d59cf1cc4b43827881d536a39c7","abstract_canon_sha256":"cfb98e4a65bfcf737db7d26d800e71c4c36ecd10f1305eafdec9bd0e7865745b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:47.076925Z","signature_b64":"d+L/Lv2JYXiv/cBcS+XaPlK3r7TX1i7FXde3HGX/Srq+UyujYf5FLrfb2sqTE/CJO4GlNuI46lNOA6bIEOhHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b3b4c096dbc4ea177bb167428b7f9bd8377e986e29425f213c726959686966f","last_reissued_at":"2026-07-05T04:46:47.076506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:47.076506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Edward Xiao, Huaizhen Tang, Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Zhen Zeng","submitted_at":"2022-08-08T10:33:36Z","abstract_excerpt":"Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity and the speech content using information-constraining bottlenecks. However, due to the pure autoencoder training method, it is difficult to evaluate the separation effect of content and speaker identity. In this paper, a novel voice conversion framework, named $\\boldsymbol T$ext $\\boldsymbol G$uided $\\boldsymbol A$utoVC(TGAVC), is proposed to more effectivel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04035","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/2208.04035/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":"2208.04035","created_at":"2026-07-05T04:46:47.076575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.04035v1","created_at":"2026-07-05T04:46:47.076575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04035","created_at":"2026-07-05T04:46:47.076575+00:00"},{"alias_kind":"pith_short_12","alias_value":"BM5UYCLNXRHK","created_at":"2026-07-05T04:46:47.076575+00:00"},{"alias_kind":"pith_short_16","alias_value":"BM5UYCLNXRHKC553","created_at":"2026-07-05T04:46:47.076575+00:00"},{"alias_kind":"pith_short_8","alias_value":"BM5UYCLN","created_at":"2026-07-05T04:46:47.076575+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/BM5UYCLNXRHKC553CZ2CRN7ZXW","json":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW.json","graph_json":"https://pith.science/api/pith-number/BM5UYCLNXRHKC553CZ2CRN7ZXW/graph.json","events_json":"https://pith.science/api/pith-number/BM5UYCLNXRHKC553CZ2CRN7ZXW/events.json","paper":"https://pith.science/paper/BM5UYCLN"},"agent_actions":{"view_html":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW","download_json":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW.json","view_paper":"https://pith.science/paper/BM5UYCLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.04035&json=true","fetch_graph":"https://pith.science/api/pith-number/BM5UYCLNXRHKC553CZ2CRN7ZXW/graph.json","fetch_events":"https://pith.science/api/pith-number/BM5UYCLNXRHKC553CZ2CRN7ZXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW/action/storage_attestation","attest_author":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW/action/author_attestation","sign_citation":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW/action/citation_signature","submit_replication":"https://pith.science/pith/BM5UYCLNXRHKC553CZ2CRN7ZXW/action/replication_record"}},"created_at":"2026-07-05T04:46:47.076575+00:00","updated_at":"2026-07-05T04:46:47.076575+00:00"}