{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XIGWAKLHQVC7ZBKZMSMQRMOL34","short_pith_number":"pith:XIGWAKLH","schema_version":"1.0","canonical_sha256":"ba0d6029678545fc8559649908b1cbdf27ab24b2b4794f45949af1f39ba1b135","source":{"kind":"arxiv","id":"1906.10508","version":3},"attestation_state":"computed","paper":{"title":"Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jing-Xuan Zhang, Li-Rong Dai, Zhen-Hua Ling","submitted_at":"2019-06-25T13:33:47Z","abstract_excerpt":"This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of"},"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":"1906.10508","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-25T13:33:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b5e120f0e295115543391de3b9b526ba5b74040e6e464a3e196c161adece1443","abstract_canon_sha256":"a13260933c08c6341cb7a1040219f451f73238116288aba29fd390b8e398654f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:50.409041Z","signature_b64":"QPENmCjUZ+yehhSg6Obz25p1mQcIOqnCP9UwuPDwb3xvzFt87+TRM3u4Cfd78K9ti860+WxaadrNwujZZm42Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba0d6029678545fc8559649908b1cbdf27ab24b2b4794f45949af1f39ba1b135","last_reissued_at":"2026-07-05T00:32:50.408604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:50.408604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jing-Xuan Zhang, Li-Rong Dai, Zhen-Hua Ling","submitted_at":"2019-06-25T13:33:47Z","abstract_excerpt":"This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10508","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/1906.10508/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":"1906.10508","created_at":"2026-07-05T00:32:50.408664+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.10508v3","created_at":"2026-07-05T00:32:50.408664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10508","created_at":"2026-07-05T00:32:50.408664+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIGWAKLHQVC7","created_at":"2026-07-05T00:32:50.408664+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIGWAKLHQVC7ZBKZ","created_at":"2026-07-05T00:32:50.408664+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIGWAKLH","created_at":"2026-07-05T00:32:50.408664+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/XIGWAKLHQVC7ZBKZMSMQRMOL34","json":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34.json","graph_json":"https://pith.science/api/pith-number/XIGWAKLHQVC7ZBKZMSMQRMOL34/graph.json","events_json":"https://pith.science/api/pith-number/XIGWAKLHQVC7ZBKZMSMQRMOL34/events.json","paper":"https://pith.science/paper/XIGWAKLH"},"agent_actions":{"view_html":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34","download_json":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34.json","view_paper":"https://pith.science/paper/XIGWAKLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.10508&json=true","fetch_graph":"https://pith.science/api/pith-number/XIGWAKLHQVC7ZBKZMSMQRMOL34/graph.json","fetch_events":"https://pith.science/api/pith-number/XIGWAKLHQVC7ZBKZMSMQRMOL34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34/action/storage_attestation","attest_author":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34/action/author_attestation","sign_citation":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34/action/citation_signature","submit_replication":"https://pith.science/pith/XIGWAKLHQVC7ZBKZMSMQRMOL34/action/replication_record"}},"created_at":"2026-07-05T00:32:50.408664+00:00","updated_at":"2026-07-05T00:32:50.408664+00:00"}