{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KM5RYHQUP6XWSATTKDWYVTLKE","short_pith_number":"pith:6KM5RYHQ","schema_version":"1.0","canonical_sha256":"f299d8e0f0a3fd7b48139a876c566b513dd59a144893e8abf96a308bb1d5681a","source":{"kind":"arxiv","id":"2401.11053","version":5},"attestation_state":"computed","paper":{"title":"StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Lei Xie, Xinsheng Wang, Yuanzhe Chen, Yuping Wang, Zhichao Wang","submitted_at":"2024-01-19T23:05:05Z","abstract_excerpt":"Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion from source semantics to acoustic features, demanding the complete source speech and limiting their deployment to real-time applications. In this paper, we introduce StreamVoice, a novel streaming LM-based model for zero-shot VC, facilitating real-time conversion given arbitrary speaker prompts and source speech. Specifically, to enable streaming capability, StreamVoice employs a fully causal context-aware LM with a"},"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":"2401.11053","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-19T23:05:05Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"953cf815ef596164c10f775978b8a79cbc5584522950b027d2d4632e438a6e52","abstract_canon_sha256":"4b6016a63293bc513ee5481d75e0198d347a0e4599f5e339c34c7a92829d38d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:49.615926Z","signature_b64":"FwFNCYIu3FmLq1Zn5NXXvFGtZMO35grkgtkZl3NqoK8+GZ9/Xj+6KCYkjWe+HTGc1Jbsd28qoMcNswFmCvjxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f299d8e0f0a3fd7b48139a876c566b513dd59a144893e8abf96a308bb1d5681a","last_reissued_at":"2026-07-05T08:45:49.615457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:49.615457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Lei Xie, Xinsheng Wang, Yuanzhe Chen, Yuping Wang, Zhichao Wang","submitted_at":"2024-01-19T23:05:05Z","abstract_excerpt":"Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion from source semantics to acoustic features, demanding the complete source speech and limiting their deployment to real-time applications. In this paper, we introduce StreamVoice, a novel streaming LM-based model for zero-shot VC, facilitating real-time conversion given arbitrary speaker prompts and source speech. Specifically, to enable streaming capability, StreamVoice employs a fully causal context-aware LM with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11053","kind":"arxiv","version":5},"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/2401.11053/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":"2401.11053","created_at":"2026-07-05T08:45:49.615514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11053v5","created_at":"2026-07-05T08:45:49.615514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11053","created_at":"2026-07-05T08:45:49.615514+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KM5RYHQUP6X","created_at":"2026-07-05T08:45:49.615514+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KM5RYHQUP6XWSAT","created_at":"2026-07-05T08:45:49.615514+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KM5RYHQ","created_at":"2026-07-05T08:45:49.615514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE","json":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE.json","graph_json":"https://pith.science/api/pith-number/6KM5RYHQUP6XWSATTKDWYVTLKE/graph.json","events_json":"https://pith.science/api/pith-number/6KM5RYHQUP6XWSATTKDWYVTLKE/events.json","paper":"https://pith.science/paper/6KM5RYHQ"},"agent_actions":{"view_html":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE","download_json":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE.json","view_paper":"https://pith.science/paper/6KM5RYHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11053&json=true","fetch_graph":"https://pith.science/api/pith-number/6KM5RYHQUP6XWSATTKDWYVTLKE/graph.json","fetch_events":"https://pith.science/api/pith-number/6KM5RYHQUP6XWSATTKDWYVTLKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/action/storage_attestation","attest_author":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/action/author_attestation","sign_citation":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/action/citation_signature","submit_replication":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/action/replication_record"}},"created_at":"2026-07-05T08:45:49.615514+00:00","updated_at":"2026-07-05T08:45:49.615514+00:00"}