{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YOREMFQQ4Y6AYEVNDNN64CJH2S","short_pith_number":"pith:YOREMFQQ","schema_version":"1.0","canonical_sha256":"c3a2461610e63c0c12ad1b5bee0927d48d70138cd746148104e5775139af9c4e","source":{"kind":"arxiv","id":"2109.06733","version":2},"attestation_state":"computed","paper":{"title":"Cross-speaker emotion disentangling and transfer for end-to-end speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang","submitted_at":"2021-09-14T14:46:47Z","abstract_excerpt":"The cross-speaker emotion transfer task in text-to-speech (TTS) synthesis particularly aims to synthesize speech for a target speaker with the emotion transferred from reference speech recorded by another (source) speaker. During the emotion transfer process, the identity information of the source speaker could also affect the synthesized results, resulting in the issue of speaker leakage. This paper proposes a new method with the aim to synthesize controllable emotional expressive speech and meanwhile maintain the target speaker's identity in the cross-speaker emotion TTS task. The proposed m"},"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":"2109.06733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-09-14T14:46:47Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e7c20b574599fe94fd294b6a8d318774a0552261577b9a95c9d357eac2aae00d","abstract_canon_sha256":"0b6a36be27699fdab7d281b0898ad0b2ca9019ff16a54637a2d8f4c6e1394c23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:36.094922Z","signature_b64":"1fgZEMsgd2CymDlUYSk+z4cSB3Tc7Xa1OUcic/GXFvEPOh68hXnQKaHyaknYaz92nX0y3QReIMGxHndNfm+sDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3a2461610e63c0c12ad1b5bee0927d48d70138cd746148104e5775139af9c4e","last_reissued_at":"2026-07-05T04:12:36.094457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:36.094457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-speaker emotion disentangling and transfer for end-to-end speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang","submitted_at":"2021-09-14T14:46:47Z","abstract_excerpt":"The cross-speaker emotion transfer task in text-to-speech (TTS) synthesis particularly aims to synthesize speech for a target speaker with the emotion transferred from reference speech recorded by another (source) speaker. During the emotion transfer process, the identity information of the source speaker could also affect the synthesized results, resulting in the issue of speaker leakage. This paper proposes a new method with the aim to synthesize controllable emotional expressive speech and meanwhile maintain the target speaker's identity in the cross-speaker emotion TTS task. The proposed m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06733","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/2109.06733/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":"2109.06733","created_at":"2026-07-05T04:12:36.094519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06733v2","created_at":"2026-07-05T04:12:36.094519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06733","created_at":"2026-07-05T04:12:36.094519+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOREMFQQ4Y6A","created_at":"2026-07-05T04:12:36.094519+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOREMFQQ4Y6AYEVN","created_at":"2026-07-05T04:12:36.094519+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOREMFQQ","created_at":"2026-07-05T04:12:36.094519+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/YOREMFQQ4Y6AYEVNDNN64CJH2S","json":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S.json","graph_json":"https://pith.science/api/pith-number/YOREMFQQ4Y6AYEVNDNN64CJH2S/graph.json","events_json":"https://pith.science/api/pith-number/YOREMFQQ4Y6AYEVNDNN64CJH2S/events.json","paper":"https://pith.science/paper/YOREMFQQ"},"agent_actions":{"view_html":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S","download_json":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S.json","view_paper":"https://pith.science/paper/YOREMFQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06733&json=true","fetch_graph":"https://pith.science/api/pith-number/YOREMFQQ4Y6AYEVNDNN64CJH2S/graph.json","fetch_events":"https://pith.science/api/pith-number/YOREMFQQ4Y6AYEVNDNN64CJH2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S/action/storage_attestation","attest_author":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S/action/author_attestation","sign_citation":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S/action/citation_signature","submit_replication":"https://pith.science/pith/YOREMFQQ4Y6AYEVNDNN64CJH2S/action/replication_record"}},"created_at":"2026-07-05T04:12:36.094519+00:00","updated_at":"2026-07-05T04:12:36.094519+00:00"}