{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7IC5JSBGSPICBQDHV6R7GVC32C","short_pith_number":"pith:7IC5JSBG","canonical_record":{"source":{"id":"1905.05879","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-14T23:19:04Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"ad5142414ba5e5af31d9e609593a4c07414238b875fcea41e56867bdf2f9c203","abstract_canon_sha256":"2e7ea584f2ca2d67b9c876d19b31f6d565ed500f48f762badbb5206857d23f26"},"schema_version":"1.0"},"canonical_sha256":"fa05d4c82693d020c067afa3f3545bd0ba264c0d36da79e3041ef76156158bfe","source":{"kind":"arxiv","id":"1905.05879","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05879","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05879v2","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05879","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"7IC5JSBGSPIC","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7IC5JSBGSPICBQDH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7IC5JSBG","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7IC5JSBGSPICBQDHV6R7GVC32C","target":"record","payload":{"canonical_record":{"source":{"id":"1905.05879","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-14T23:19:04Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"ad5142414ba5e5af31d9e609593a4c07414238b875fcea41e56867bdf2f9c203","abstract_canon_sha256":"2e7ea584f2ca2d67b9c876d19b31f6d565ed500f48f762badbb5206857d23f26"},"schema_version":"1.0"},"canonical_sha256":"fa05d4c82693d020c067afa3f3545bd0ba264c0d36da79e3041ef76156158bfe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.143796Z","signature_b64":"eqEc9o6dGaxbuwvFA2zbx9mEuFZVj2JvYZ2R6QFQ4bPqirLcPsTPReXrdtd16o+lpX8+k7il1AewnQ1r1r3+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa05d4c82693d020c067afa3f3545bd0ba264c0d36da79e3041ef76156158bfe","last_reissued_at":"2026-05-17T23:44:02.143272Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.143272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.05879","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+ow/HTy1tFacR5M5y72yqOxqifaNMFrlbmEbSVFuI2EM/H1LS59RxvUJ0jn1/NzLHLBAmZ8u5xEyKUoNjc0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:39:24.545428Z"},"content_sha256":"ee50f2d7879b0d999c282ed21cc0c454e3d6399e6c4f7e50e31d920444974cc9","schema_version":"1.0","event_id":"sha256:ee50f2d7879b0d999c282ed21cc0c454e3d6399e6c4f7e50e31d920444974cc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7IC5JSBGSPICBQDHV6R7GVC32C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Kaizhi Qian, Mark Hasegawa-Johnson, Shiyu Chang, Xuesong Yang, Yang Zhang","submitted_at":"2019-05-14T23:19:04Z","abstract_excerpt":"Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial networks (GAN) and conditional variational autoencoder (CVAE), are being applied as new solutions in this field. However, GAN training is sophisticated and difficult, and there is no strong evidence that its generated speech is of good perceptual quality. On the other hand, CVAE training is simple but does not come with the distribution-matching property of a GAN. In this paper, we propose a new style transfer scheme that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05879","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pXSOTQFHypSbQijfabbKHNhvT86OX9JU90l6BSQLKNJ0btT+y2ZmEe/Nt94hY/2CudsdxRtp4H3n5lQ1SBMZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:39:24.545835Z"},"content_sha256":"7bc8a48ab83c69ec446ace07656e01b8007b531cf26d0f246f1ee03e673833b4","schema_version":"1.0","event_id":"sha256:7bc8a48ab83c69ec446ace07656e01b8007b531cf26d0f246f1ee03e673833b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7IC5JSBGSPICBQDHV6R7GVC32C/bundle.json","state_url":"https://pith.science/pith/7IC5JSBGSPICBQDHV6R7GVC32C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7IC5JSBGSPICBQDHV6R7GVC32C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T01:39:24Z","links":{"resolver":"https://pith.science/pith/7IC5JSBGSPICBQDHV6R7GVC32C","bundle":"https://pith.science/pith/7IC5JSBGSPICBQDHV6R7GVC32C/bundle.json","state":"https://pith.science/pith/7IC5JSBGSPICBQDHV6R7GVC32C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7IC5JSBGSPICBQDHV6R7GVC32C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7IC5JSBGSPICBQDHV6R7GVC32C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e7ea584f2ca2d67b9c876d19b31f6d565ed500f48f762badbb5206857d23f26","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-14T23:19:04Z","title_canon_sha256":"ad5142414ba5e5af31d9e609593a4c07414238b875fcea41e56867bdf2f9c203"},"schema_version":"1.0","source":{"id":"1905.05879","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05879","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05879v2","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05879","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"7IC5JSBGSPIC","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7IC5JSBGSPICBQDH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7IC5JSBG","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:7bc8a48ab83c69ec446ace07656e01b8007b531cf26d0f246f1ee03e673833b4","target":"graph","created_at":"2026-05-17T23:44:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial networks (GAN) and conditional variational autoencoder (CVAE), are being applied as new solutions in this field. However, GAN training is sophisticated and difficult, and there is no strong evidence that its generated speech is of good perceptual quality. On the other hand, CVAE training is simple but does not come with the distribution-matching property of a GAN. In this paper, we propose a new style transfer scheme that","authors_text":"Kaizhi Qian, Mark Hasegawa-Johnson, Shiyu Chang, Xuesong Yang, Yang Zhang","cross_cats":["cs.AI","cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-14T23:19:04Z","title":"AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05879","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ee50f2d7879b0d999c282ed21cc0c454e3d6399e6c4f7e50e31d920444974cc9","target":"record","created_at":"2026-05-17T23:44:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2e7ea584f2ca2d67b9c876d19b31f6d565ed500f48f762badbb5206857d23f26","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-14T23:19:04Z","title_canon_sha256":"ad5142414ba5e5af31d9e609593a4c07414238b875fcea41e56867bdf2f9c203"},"schema_version":"1.0","source":{"id":"1905.05879","kind":"arxiv","version":2}},"canonical_sha256":"fa05d4c82693d020c067afa3f3545bd0ba264c0d36da79e3041ef76156158bfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa05d4c82693d020c067afa3f3545bd0ba264c0d36da79e3041ef76156158bfe","first_computed_at":"2026-05-17T23:44:02.143272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:02.143272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eqEc9o6dGaxbuwvFA2zbx9mEuFZVj2JvYZ2R6QFQ4bPqirLcPsTPReXrdtd16o+lpX8+k7il1AewnQ1r1r3+Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:02.143796Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05879","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee50f2d7879b0d999c282ed21cc0c454e3d6399e6c4f7e50e31d920444974cc9","sha256:7bc8a48ab83c69ec446ace07656e01b8007b531cf26d0f246f1ee03e673833b4"],"state_sha256":"e2bd520a832db3ab989ad89bf0f005a74a48ff44b28c329edeb8c93f8cd91019"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"doKTFFrGeQoGbKHOoUIXASlStIGYwHd/NemOTapELfDuYK8s1C2epKqVohk4HMWvAOuAeOgR7W28qLxHDnO/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:39:24.549334Z","bundle_sha256":"f05ac5f124faf28c59328d2f856b6c4c20d2501bfc963827a49e2c75c7893c98"}}