{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GJN5QP2F4T6JQAQU75CEERYLTF","short_pith_number":"pith:GJN5QP2F","schema_version":"1.0","canonical_sha256":"325bd83f45e4fc980214ff4442470b9943ae608c049f304922b0175bf59d9220","source":{"kind":"arxiv","id":"1808.05092","version":3},"attestation_state":"computed","paper":{"title":"ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"stat.ML","authors_text":"Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo, Takuhiro Kaneko","submitted_at":"2018-08-13T23:31:01Z","abstract_excerpt":"This paper proposes a non-parallel many-to-many voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE (ACVAE). The proposed method has three key features. First, it adopts fully convolutional architectures to construct the encoder and decoder networks so that the networks can learn conversion rules that capture time dependencies in the acoustic feature sequences of source and target speech. Second, it uses an information-theoretic regularization for the model training to ensure that the information in the attribute 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":"1808.05092","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-13T23:31:01Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"88967c56d2edb25bb82840e66da4cec6e952fcb74ac2e8cafca12386845b219c","abstract_canon_sha256":"02b9b3c17f87a63e667f97b148f32bf00aecc5ec6093e08e5dae6bcf30417504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:46.598662Z","signature_b64":"VJeIlnn5Hp41uxqu7t3EmnsvIVcjN/W7fgHiae19Gdv+sufNkKfolvctECeHAB2P5gc7iSFotcz+NtmLRiizBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325bd83f45e4fc980214ff4442470b9943ae608c049f304922b0175bf59d9220","last_reissued_at":"2026-07-05T01:41:46.598179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:46.598179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"stat.ML","authors_text":"Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo, Takuhiro Kaneko","submitted_at":"2018-08-13T23:31:01Z","abstract_excerpt":"This paper proposes a non-parallel many-to-many voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE (ACVAE). The proposed method has three key features. First, it adopts fully convolutional architectures to construct the encoder and decoder networks so that the networks can learn conversion rules that capture time dependencies in the acoustic feature sequences of source and target speech. Second, it uses an information-theoretic regularization for the model training to ensure that the information in the attribute clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05092","kind":"arxiv","version":3},"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/1808.05092/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":"1808.05092","created_at":"2026-07-05T01:41:46.598234+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05092v3","created_at":"2026-07-05T01:41:46.598234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05092","created_at":"2026-07-05T01:41:46.598234+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJN5QP2F4T6J","created_at":"2026-07-05T01:41:46.598234+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJN5QP2F4T6JQAQU","created_at":"2026-07-05T01:41:46.598234+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJN5QP2F","created_at":"2026-07-05T01:41:46.598234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.10185","citing_title":"Non-Parallel Voice Conversion with Cyclic Variational Autoencoder","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF","json":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF.json","graph_json":"https://pith.science/api/pith-number/GJN5QP2F4T6JQAQU75CEERYLTF/graph.json","events_json":"https://pith.science/api/pith-number/GJN5QP2F4T6JQAQU75CEERYLTF/events.json","paper":"https://pith.science/paper/GJN5QP2F"},"agent_actions":{"view_html":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF","download_json":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF.json","view_paper":"https://pith.science/paper/GJN5QP2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05092&json=true","fetch_graph":"https://pith.science/api/pith-number/GJN5QP2F4T6JQAQU75CEERYLTF/graph.json","fetch_events":"https://pith.science/api/pith-number/GJN5QP2F4T6JQAQU75CEERYLTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF/action/storage_attestation","attest_author":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF/action/author_attestation","sign_citation":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF/action/citation_signature","submit_replication":"https://pith.science/pith/GJN5QP2F4T6JQAQU75CEERYLTF/action/replication_record"}},"created_at":"2026-07-05T01:41:46.598234+00:00","updated_at":"2026-07-05T01:41:46.598234+00:00"}