{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G4HP2JGP25XTLUJZ2UKV2RP3P5","short_pith_number":"pith:G4HP2JGP","schema_version":"1.0","canonical_sha256":"370efd24cfd76f35d139d5155d45fb7f7dcfdf3079e5d0502c090d1d8b6db0c8","source":{"kind":"arxiv","id":"2106.08741","version":3},"attestation_state":"computed","paper":{"title":"Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fengyu Yang, Hai Li, Haitao Chen, Hongqiang Du, Lei Xie, Tao Li, Wendong Gan, Xinyong Zhou, Zhichao Wang","submitted_at":"2021-06-16T12:34:47Z","abstract_excerpt":"Current voice conversion (VC) methods can successfully convert timbre of the audio. As modeling source audio's prosody effectively is a challenging task, there are still limitations of transferring source style to the converted speech. This study proposes a source style transfer method based on recognition-synthesis framework. Previously in speech generation task, prosody can be modeled explicitly with prosodic features or implicitly with a latent prosody extractor. In this paper, taking advantages of both, we model the prosody in a hybrid manner, which effectively combines explicit and implic"},"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":"2106.08741","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-16T12:34:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"47654f22b8402b62d8344e724f6d8af96892129a710fdfe0639b85ea45fb4e63","abstract_canon_sha256":"8d888a99e47663a1b27400813df886bd4452bef81c2e29d7daaaf7f934e41bcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:28.682283Z","signature_b64":"gZc0+xrX5XJFFQouQ4vcPqcBZsPy3TNrbYYgq3ozxtcQREmMxW2oqwcF+0KtFaclqbOXdFZeQmjx0tNvhuieAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370efd24cfd76f35d139d5155d45fb7f7dcfdf3079e5d0502c090d1d8b6db0c8","last_reissued_at":"2026-07-05T02:52:28.681813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:28.681813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fengyu Yang, Hai Li, Haitao Chen, Hongqiang Du, Lei Xie, Tao Li, Wendong Gan, Xinyong Zhou, Zhichao Wang","submitted_at":"2021-06-16T12:34:47Z","abstract_excerpt":"Current voice conversion (VC) methods can successfully convert timbre of the audio. As modeling source audio's prosody effectively is a challenging task, there are still limitations of transferring source style to the converted speech. This study proposes a source style transfer method based on recognition-synthesis framework. Previously in speech generation task, prosody can be modeled explicitly with prosodic features or implicitly with a latent prosody extractor. In this paper, taking advantages of both, we model the prosody in a hybrid manner, which effectively combines explicit and implic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08741","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/2106.08741/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":"2106.08741","created_at":"2026-07-05T02:52:28.681874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08741v3","created_at":"2026-07-05T02:52:28.681874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08741","created_at":"2026-07-05T02:52:28.681874+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4HP2JGP25XT","created_at":"2026-07-05T02:52:28.681874+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4HP2JGP25XTLUJZ","created_at":"2026-07-05T02:52:28.681874+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4HP2JGP","created_at":"2026-07-05T02:52:28.681874+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/G4HP2JGP25XTLUJZ2UKV2RP3P5","json":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5.json","graph_json":"https://pith.science/api/pith-number/G4HP2JGP25XTLUJZ2UKV2RP3P5/graph.json","events_json":"https://pith.science/api/pith-number/G4HP2JGP25XTLUJZ2UKV2RP3P5/events.json","paper":"https://pith.science/paper/G4HP2JGP"},"agent_actions":{"view_html":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5","download_json":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5.json","view_paper":"https://pith.science/paper/G4HP2JGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08741&json=true","fetch_graph":"https://pith.science/api/pith-number/G4HP2JGP25XTLUJZ2UKV2RP3P5/graph.json","fetch_events":"https://pith.science/api/pith-number/G4HP2JGP25XTLUJZ2UKV2RP3P5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5/action/storage_attestation","attest_author":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5/action/author_attestation","sign_citation":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5/action/citation_signature","submit_replication":"https://pith.science/pith/G4HP2JGP25XTLUJZ2UKV2RP3P5/action/replication_record"}},"created_at":"2026-07-05T02:52:28.681874+00:00","updated_at":"2026-07-05T02:52:28.681874+00:00"}