{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UJWKIH7U46OJK3D2WLJ6MDJ2IS","short_pith_number":"pith:UJWKIH7U","canonical_record":{"source":{"id":"2409.13910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T21:27:13Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"35ec36044bfdc41bbf87104edb91a5e961dd8c17eedfc591a952d513cdf16881","abstract_canon_sha256":"b96d3e1f0cadc86b457d2b8770f2a184ded3f2942d3c1a58f2d96a2fb972d41a"},"schema_version":"1.0"},"canonical_sha256":"a26ca41ff4e79c956c7ab2d3e60d3a44b752f4c2e79499f1584f0d8919af6909","source":{"kind":"arxiv","id":"2409.13910","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13910","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13910v1","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13910","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"UJWKIH7U46OJ","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"UJWKIH7U46OJK3D2","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"UJWKIH7U","created_at":"2026-07-05T09:10:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UJWKIH7U46OJK3D2WLJ6MDJ2IS","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T21:27:13Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"35ec36044bfdc41bbf87104edb91a5e961dd8c17eedfc591a952d513cdf16881","abstract_canon_sha256":"b96d3e1f0cadc86b457d2b8770f2a184ded3f2942d3c1a58f2d96a2fb972d41a"},"schema_version":"1.0"},"canonical_sha256":"a26ca41ff4e79c956c7ab2d3e60d3a44b752f4c2e79499f1584f0d8919af6909","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:08.664269Z","signature_b64":"fDzHHLtHGuH8ro/NX94TMPX/KsPhVXG3uPXKcxlpjlp9wbkgKKNhxYxP87lEkAT7d8y+h2ULgpOwDzIFfCDWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a26ca41ff4e79c956c7ab2d3e60d3a44b752f4c2e79499f1584f0d8919af6909","last_reissued_at":"2026-07-05T09:10:08.663794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:08.663794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13910","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLRJE6e2zcZgPIf/ZjaammtUBkQXnf0qcNsmS3LB06Oqvo4nml6QZEPbViD9q41RbD0ZtzpmEtkaxDeNOMVWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:08:08.176506Z"},"content_sha256":"7a4fe990d6a9bb2ba8771708ea1d312b8a542962e8372aacadec5f3f5b9119e8","schema_version":"1.0","event_id":"sha256:7a4fe990d6a9bb2ba8771708ea1d312b8a542962e8372aacadec5f3f5b9119e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UJWKIH7U46OJK3D2WLJ6MDJ2IS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-shot Cross-lingual Voice Transfer for TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Gary Wang, Isaac Elias, Kyle Kastner, Youzheng Chen","submitted_at":"2024-09-20T21:27:13Z","abstract_excerpt":"In this paper, we introduce a zero-shot Voice Transfer (VT) module that can be seamlessly integrated into a multi-lingual Text-to-speech (TTS) system to transfer an individual's voice across languages. Our proposed VT module comprises a speaker-encoder that processes reference speech, a bottleneck layer, and residual adapters, connected to preexisting TTS layers. We compare the performance of various configurations of these components and report Mean Opinion Score (MOS) and Speaker Similarity across languages. Using a single English reference speech per speaker, we achieve an average voice tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13910","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/2409.13910/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":"2026-07-05T09:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AeEzJbUJjF0otaJyLeFYZOVO7GwnQ8ppFgtE33DWvSVBYQjzqfv3jf642IIF2KvOFEc3Hn6Qtk5ApTA9E2kDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:08:08.177461Z"},"content_sha256":"8f593188aacb6b2b28946a275b08cc2ecb981f4fc429c660afc2693d1729ca58","schema_version":"1.0","event_id":"sha256:8f593188aacb6b2b28946a275b08cc2ecb981f4fc429c660afc2693d1729ca58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS/bundle.json","state_url":"https://pith.science/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS/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":"2026-08-10T09:08:08Z","links":{"resolver":"https://pith.science/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS","bundle":"https://pith.science/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS/bundle.json","state":"https://pith.science/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJWKIH7U46OJK3D2WLJ6MDJ2IS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UJWKIH7U46OJK3D2WLJ6MDJ2IS","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":"b96d3e1f0cadc86b457d2b8770f2a184ded3f2942d3c1a58f2d96a2fb972d41a","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T21:27:13Z","title_canon_sha256":"35ec36044bfdc41bbf87104edb91a5e961dd8c17eedfc591a952d513cdf16881"},"schema_version":"1.0","source":{"id":"2409.13910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13910","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13910v1","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13910","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"UJWKIH7U46OJ","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"UJWKIH7U46OJK3D2","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"UJWKIH7U","created_at":"2026-07-05T09:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:8f593188aacb6b2b28946a275b08cc2ecb981f4fc429c660afc2693d1729ca58","target":"graph","created_at":"2026-07-05T09:10:08Z","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/2409.13910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a zero-shot Voice Transfer (VT) module that can be seamlessly integrated into a multi-lingual Text-to-speech (TTS) system to transfer an individual's voice across languages. Our proposed VT module comprises a speaker-encoder that processes reference speech, a bottleneck layer, and residual adapters, connected to preexisting TTS layers. We compare the performance of various configurations of these components and report Mean Opinion Score (MOS) and Speaker Similarity across languages. Using a single English reference speech per speaker, we achieve an average voice tra","authors_text":"Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Gary Wang, Isaac Elias, Kyle Kastner, Youzheng Chen","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T21:27:13Z","title":"Zero-shot Cross-lingual Voice Transfer for TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13910","kind":"arxiv","version":1},"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":"sha256:7a4fe990d6a9bb2ba8771708ea1d312b8a542962e8372aacadec5f3f5b9119e8","target":"record","created_at":"2026-07-05T09:10:08Z","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":"b96d3e1f0cadc86b457d2b8770f2a184ded3f2942d3c1a58f2d96a2fb972d41a","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T21:27:13Z","title_canon_sha256":"35ec36044bfdc41bbf87104edb91a5e961dd8c17eedfc591a952d513cdf16881"},"schema_version":"1.0","source":{"id":"2409.13910","kind":"arxiv","version":1}},"canonical_sha256":"a26ca41ff4e79c956c7ab2d3e60d3a44b752f4c2e79499f1584f0d8919af6909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a26ca41ff4e79c956c7ab2d3e60d3a44b752f4c2e79499f1584f0d8919af6909","first_computed_at":"2026-07-05T09:10:08.663794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:08.663794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fDzHHLtHGuH8ro/NX94TMPX/KsPhVXG3uPXKcxlpjlp9wbkgKKNhxYxP87lEkAT7d8y+h2ULgpOwDzIFfCDWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:08.664269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a4fe990d6a9bb2ba8771708ea1d312b8a542962e8372aacadec5f3f5b9119e8","sha256:8f593188aacb6b2b28946a275b08cc2ecb981f4fc429c660afc2693d1729ca58"],"state_sha256":"e3d9937c2c597402bd0a2b356f54a6f914b2b4b194c7fc6e2e4d2fcc28310169"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLZPXIIVu69TVrfQEFaYSVJ2ZiE/EYrfy/5hGjZ+6YwvL3mm5JaHytVaeXbVkUm/LY10G/RQL4Cr9WwJ/7obBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:08:08.183620Z","bundle_sha256":"3d1c8c20bd64f0021d7e4f06c2d4f655e0688a50674d838960feeb041b97cf5e"}}