{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RBOUIORGYLE5DIFYEVWZ2KOKCC","short_pith_number":"pith:RBOUIORG","schema_version":"1.0","canonical_sha256":"885d443a26c2c9d1a0b8256d9d29ca108abad62126ce65788e86ba1798b83842","source":{"kind":"arxiv","id":"2303.07711","version":1},"attestation_state":"computed","paper":{"title":"Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunyu Qiang, Hao Che, Peng Yang, Xiaorui Wang, Ying Zhang, Zhongyuan Wang","submitted_at":"2023-03-14T08:52:58Z","abstract_excerpt":"Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesized speech of a target speaker's timbre. In most previous methods, the synthesized fine-grained prosody features often represent the source speaker's average style, similar to the one-to-many problem(i.e., multiple prosody variations correspond to the same text). In response to this problem, a strength-controlled semi-supervised style extractor is proposed to disentangle the style from content and timbre, improving the representation and interpretability of the global style embedding, w"},"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":"2303.07711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T08:52:58Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"0b4378da7c3566501ef097074dd7528b2d2a220783d469c74a5638608c289ad3","abstract_canon_sha256":"2c61530c936602d27301d07a0d1a66469a9c7e8b506d9191a1bec8c7883fed09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:10.226435Z","signature_b64":"bhEAL17Oi4c0K9jb1zwLk+S7eLqdAiHqwJrdK3F4EHf6bvVjTEOet6Kk4vhuyo6o0ozWOEDPfqG0cf6iHLvQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"885d443a26c2c9d1a0b8256d9d29ca108abad62126ce65788e86ba1798b83842","last_reissued_at":"2026-07-05T05:51:10.226012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:10.226012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunyu Qiang, Hao Che, Peng Yang, Xiaorui Wang, Ying Zhang, Zhongyuan Wang","submitted_at":"2023-03-14T08:52:58Z","abstract_excerpt":"Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesized speech of a target speaker's timbre. In most previous methods, the synthesized fine-grained prosody features often represent the source speaker's average style, similar to the one-to-many problem(i.e., multiple prosody variations correspond to the same text). In response to this problem, a strength-controlled semi-supervised style extractor is proposed to disentangle the style from content and timbre, improving the representation and interpretability of the global style embedding, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07711","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/2303.07711/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":"2303.07711","created_at":"2026-07-05T05:51:10.226073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07711v1","created_at":"2026-07-05T05:51:10.226073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07711","created_at":"2026-07-05T05:51:10.226073+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBOUIORGYLE5","created_at":"2026-07-05T05:51:10.226073+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBOUIORGYLE5DIFY","created_at":"2026-07-05T05:51:10.226073+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBOUIORG","created_at":"2026-07-05T05:51:10.226073+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/RBOUIORGYLE5DIFYEVWZ2KOKCC","json":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC.json","graph_json":"https://pith.science/api/pith-number/RBOUIORGYLE5DIFYEVWZ2KOKCC/graph.json","events_json":"https://pith.science/api/pith-number/RBOUIORGYLE5DIFYEVWZ2KOKCC/events.json","paper":"https://pith.science/paper/RBOUIORG"},"agent_actions":{"view_html":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC","download_json":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC.json","view_paper":"https://pith.science/paper/RBOUIORG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07711&json=true","fetch_graph":"https://pith.science/api/pith-number/RBOUIORGYLE5DIFYEVWZ2KOKCC/graph.json","fetch_events":"https://pith.science/api/pith-number/RBOUIORGYLE5DIFYEVWZ2KOKCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC/action/storage_attestation","attest_author":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC/action/author_attestation","sign_citation":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC/action/citation_signature","submit_replication":"https://pith.science/pith/RBOUIORGYLE5DIFYEVWZ2KOKCC/action/replication_record"}},"created_at":"2026-07-05T05:51:10.226073+00:00","updated_at":"2026-07-05T05:51:10.226073+00:00"}