{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6KM5RYHQUP6XWSATTKDWYVTLKE","short_pith_number":"pith:6KM5RYHQ","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"},"canonical_sha256":"f299d8e0f0a3fd7b48139a876c566b513dd59a144893e8abf96a308bb1d5681a","source":{"kind":"arxiv","id":"2401.11053","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11053","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11053v5","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11053","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"6KM5RYHQUP6X","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"pith_short_16","alias_value":"6KM5RYHQUP6XWSAT","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"pith_short_8","alias_value":"6KM5RYHQ","created_at":"2026-07-05T08:45:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6KM5RYHQUP6XWSATTKDWYVTLKE","target":"record","payload":{"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"},"canonical_sha256":"f299d8e0f0a3fd7b48139a876c566b513dd59a144893e8abf96a308bb1d5681a","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"},"source_kind":"arxiv","source_id":"2401.11053","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TI0SRrbR+MgPW41UszGSVE+T4V1gGbd3ZEhQ8EgivZrXdUC4yZ9CMCK4y+1gekj7WW7e1TrxM8DMUBbNB7agAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:30:47.218459Z"},"content_sha256":"54296c9a6db739a1f95fe4fcf89d266ecd0cb641b9358779e4c6ba07edf97129","schema_version":"1.0","event_id":"sha256:54296c9a6db739a1f95fe4fcf89d266ecd0cb641b9358779e4c6ba07edf97129"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6KM5RYHQUP6XWSATTKDWYVTLKE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dj/yFEHCx0Qq1bXGr7UIC6zhANUgFjbVEhjkryyFYPOM5u7SNbQzrUKyvhueONF+anIlQM7T29tDWkVAWcGEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:30:47.218829Z"},"content_sha256":"af12005eec0d5493d0f6f92c715c6ee318fb3631d221e309718106536c6bf79b","schema_version":"1.0","event_id":"sha256:af12005eec0d5493d0f6f92c715c6ee318fb3631d221e309718106536c6bf79b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/bundle.json","state_url":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:30:47Z","links":{"resolver":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE","bundle":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/bundle.json","state":"https://pith.science/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KM5RYHQUP6XWSATTKDWYVTLKE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KM5RYHQUP6XWSATTKDWYVTLKE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4b6016a63293bc513ee5481d75e0198d347a0e4599f5e339c34c7a92829d38d8","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-19T23:05:05Z","title_canon_sha256":"953cf815ef596164c10f775978b8a79cbc5584522950b027d2d4632e438a6e52"},"schema_version":"1.0","source":{"id":"2401.11053","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11053","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11053v5","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11053","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"6KM5RYHQUP6X","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"pith_short_16","alias_value":"6KM5RYHQUP6XWSAT","created_at":"2026-07-05T08:45:49Z"},{"alias_kind":"pith_short_8","alias_value":"6KM5RYHQ","created_at":"2026-07-05T08:45:49Z"}],"graph_snapshots":[{"event_id":"sha256:af12005eec0d5493d0f6f92c715c6ee318fb3631d221e309718106536c6bf79b","target":"graph","created_at":"2026-07-05T08:45:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.11053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lei Xie, Xinsheng Wang, Yuanzhe Chen, Yuping Wang, Zhichao Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-19T23:05:05Z","title":"StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11053","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:54296c9a6db739a1f95fe4fcf89d266ecd0cb641b9358779e4c6ba07edf97129","target":"record","created_at":"2026-07-05T08:45:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4b6016a63293bc513ee5481d75e0198d347a0e4599f5e339c34c7a92829d38d8","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-19T23:05:05Z","title_canon_sha256":"953cf815ef596164c10f775978b8a79cbc5584522950b027d2d4632e438a6e52"},"schema_version":"1.0","source":{"id":"2401.11053","kind":"arxiv","version":5}},"canonical_sha256":"f299d8e0f0a3fd7b48139a876c566b513dd59a144893e8abf96a308bb1d5681a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f299d8e0f0a3fd7b48139a876c566b513dd59a144893e8abf96a308bb1d5681a","first_computed_at":"2026-07-05T08:45:49.615457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:49.615457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FwFNCYIu3FmLq1Zn5NXXvFGtZMO35grkgtkZl3NqoK8+GZ9/Xj+6KCYkjWe+HTGc1Jbsd28qoMcNswFmCvjxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:49.615926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11053","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54296c9a6db739a1f95fe4fcf89d266ecd0cb641b9358779e4c6ba07edf97129","sha256:af12005eec0d5493d0f6f92c715c6ee318fb3631d221e309718106536c6bf79b"],"state_sha256":"9eaade8f9f36073ffa447a1d0c5b984bd7094f3526044b9ef27f1c918e12cc29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzyDx76u7ic9oXfd+GEqtFQpu7EnRPwFhgSChKNcm1UeHnkhMWbv2s/0+LfSFlEcEV3pb3wMQmWkHlSiqV9xDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:30:47.220798Z","bundle_sha256":"6d6e6e17ee6f9d906ca7ca4aeede46a566d845923e8ef06ba89a9f36edb45780"}}