{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6IJTL75ZMZISQWG5NJDMNFDY5H","short_pith_number":"pith:6IJTL75Z","schema_version":"1.0","canonical_sha256":"f21335ffb966512858dd6a46c69478e9e2e2c9d52289311e2248a42dbd62b190","source":{"kind":"arxiv","id":"2409.05004","version":2},"attestation_state":"computed","paper":{"title":"Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Junichi Yamagishi, Mingyang Zhang, Shuai Wang, Xuechen Liu, Yanmin Qian, Zhengyang Chen","submitted_at":"2024-09-08T07:24:03Z","abstract_excerpt":"Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic"},"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":"2409.05004","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-08T07:24:03Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7465da3cc18e1810686b8b9b76a5a2d1e7391d6a5703ff528d691af16c74f831","abstract_canon_sha256":"1450cf84eff72c32e15bc9e570c92eed7b6dd0b3e2e2852622e8398d0009204c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:19.484814Z","signature_b64":"cSXlaJxzAobv6NoNw/JXbVI5QR1mCrGC7lEHiZG4+S4zJcSgW1ysIATVeybifafFFQBYVAJGeBfro/13xy6lDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f21335ffb966512858dd6a46c69478e9e2e2c9d52289311e2248a42dbd62b190","last_reissued_at":"2026-07-05T09:05:19.484290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:19.484290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Junichi Yamagishi, Mingyang Zhang, Shuai Wang, Xuechen Liu, Yanmin Qian, Zhengyang Chen","submitted_at":"2024-09-08T07:24:03Z","abstract_excerpt":"Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05004","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/2409.05004/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":"2409.05004","created_at":"2026-07-05T09:05:19.484358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05004v2","created_at":"2026-07-05T09:05:19.484358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05004","created_at":"2026-07-05T09:05:19.484358+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IJTL75ZMZIS","created_at":"2026-07-05T09:05:19.484358+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IJTL75ZMZISQWG5","created_at":"2026-07-05T09:05:19.484358+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IJTL75Z","created_at":"2026-07-05T09:05:19.484358+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/6IJTL75ZMZISQWG5NJDMNFDY5H","json":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H.json","graph_json":"https://pith.science/api/pith-number/6IJTL75ZMZISQWG5NJDMNFDY5H/graph.json","events_json":"https://pith.science/api/pith-number/6IJTL75ZMZISQWG5NJDMNFDY5H/events.json","paper":"https://pith.science/paper/6IJTL75Z"},"agent_actions":{"view_html":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H","download_json":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H.json","view_paper":"https://pith.science/paper/6IJTL75Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05004&json=true","fetch_graph":"https://pith.science/api/pith-number/6IJTL75ZMZISQWG5NJDMNFDY5H/graph.json","fetch_events":"https://pith.science/api/pith-number/6IJTL75ZMZISQWG5NJDMNFDY5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H/action/storage_attestation","attest_author":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H/action/author_attestation","sign_citation":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H/action/citation_signature","submit_replication":"https://pith.science/pith/6IJTL75ZMZISQWG5NJDMNFDY5H/action/replication_record"}},"created_at":"2026-07-05T09:05:19.484358+00:00","updated_at":"2026-07-05T09:05:19.484358+00:00"}