{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6TXQ4XI2WTKGEFKPBLDAPYCEOM","short_pith_number":"pith:6TXQ4XI2","canonical_record":{"source":{"id":"2210.13771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-25T05:12:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4f2ff66906d792fa9ba74d31f21675aef23ee16f23cb860f5da0f609a6490572","abstract_canon_sha256":"2c73f99a9462fed963f3e4583c06fd9d09a9855d1913658d5c34dee8f18c0b68"},"schema_version":"1.0"},"canonical_sha256":"f4ef0e5d1ab4d462154f0ac607e0447325dbcc82739ca69a7fa6907f5d9363f0","source":{"kind":"arxiv","id":"2210.13771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13771","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13771v1","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13771","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"6TXQ4XI2WTKG","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"6TXQ4XI2WTKGEFKP","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"6TXQ4XI2","created_at":"2026-07-05T05:10:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6TXQ4XI2WTKGEFKPBLDAPYCEOM","target":"record","payload":{"canonical_record":{"source":{"id":"2210.13771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-25T05:12:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4f2ff66906d792fa9ba74d31f21675aef23ee16f23cb860f5da0f609a6490572","abstract_canon_sha256":"2c73f99a9462fed963f3e4583c06fd9d09a9855d1913658d5c34dee8f18c0b68"},"schema_version":"1.0"},"canonical_sha256":"f4ef0e5d1ab4d462154f0ac607e0447325dbcc82739ca69a7fa6907f5d9363f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:22.287842Z","signature_b64":"Od2j4xwSddRY9xtor9T0mAOL8DATmtheOg90k802/o5pJiJArapj1vADw783xQ+I/8P+stP5mqD3GSSEXIdLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4ef0e5d1ab4d462154f0ac607e0447325dbcc82739ca69a7fa6907f5d9363f0","last_reissued_at":"2026-07-05T05:10:22.287245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:22.287245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.13771","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":"2026-07-05T05:10:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K3uFUBLhyJX59jeQsC7OavGjoEGi/G13YEtF4CHfiTxpMSYSKzqQb0HoH2lhv7w+NYMaZlLbns4lisLvsq2aDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:37:07.148035Z"},"content_sha256":"e943324228663a8e39e2dbf463954d776bae5a7cb2eb96ff7cb95b1ba2352625","schema_version":"1.0","event_id":"sha256:e943324228663a8e39e2dbf463954d776bae5a7cb2eb96ff7cb95b1ba2352625"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6TXQ4XI2WTKGEFKPBLDAPYCEOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangled Speech Representation Learning for One-Shot Cross-lingual Voice Conversion Using $\\beta$-VAE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Disong Wang, Helen Meng, Hui Lu, Xixin Wu, Xunying Liu, Zhiyong Wu","submitted_at":"2022-10-25T05:12:47Z","abstract_excerpt":"We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the effectiveness of the disentanglement. Inspired by $\\beta$-VAE, we introduce a learning objective that balances between the information captured by the content and speaker representations. In addition, the inductive biases from the architectural design and the training dataset further encourage the desired disentanglement. Both objective and subjective evaluations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13771","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/2210.13771/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":"2026-07-05T05:10:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xs2Q6GZ+3R4QLkYxayTS0nydfyUbyDHneldjd8mLY7jHjGYn3uREHUl3hzvyq0oaufT0xQVrIc/ZfzUL29YMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:37:07.148466Z"},"content_sha256":"9313aeb9aeb57c120479d7003fb4b659a42bbcefba1c559f8e26c82b316a2918","schema_version":"1.0","event_id":"sha256:9313aeb9aeb57c120479d7003fb4b659a42bbcefba1c559f8e26c82b316a2918"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM/bundle.json","state_url":"https://pith.science/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM/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":"2026-07-05T14:37:07Z","links":{"resolver":"https://pith.science/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM","bundle":"https://pith.science/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM/bundle.json","state":"https://pith.science/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TXQ4XI2WTKGEFKPBLDAPYCEOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6TXQ4XI2WTKGEFKPBLDAPYCEOM","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":"2c73f99a9462fed963f3e4583c06fd9d09a9855d1913658d5c34dee8f18c0b68","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-25T05:12:47Z","title_canon_sha256":"4f2ff66906d792fa9ba74d31f21675aef23ee16f23cb860f5da0f609a6490572"},"schema_version":"1.0","source":{"id":"2210.13771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13771","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13771v1","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13771","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"6TXQ4XI2WTKG","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"6TXQ4XI2WTKGEFKP","created_at":"2026-07-05T05:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"6TXQ4XI2","created_at":"2026-07-05T05:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:9313aeb9aeb57c120479d7003fb4b659a42bbcefba1c559f8e26c82b316a2918","target":"graph","created_at":"2026-07-05T05:10:22Z","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/2210.13771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the effectiveness of the disentanglement. Inspired by $\\beta$-VAE, we introduce a learning objective that balances between the information captured by the content and speaker representations. In addition, the inductive biases from the architectural design and the training dataset further encourage the desired disentanglement. Both objective and subjective evaluations ","authors_text":"Disong Wang, Helen Meng, Hui Lu, Xixin Wu, Xunying Liu, Zhiyong Wu","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-25T05:12:47Z","title":"Disentangled Speech Representation Learning for One-Shot Cross-lingual Voice Conversion Using $\\beta$-VAE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13771","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:e943324228663a8e39e2dbf463954d776bae5a7cb2eb96ff7cb95b1ba2352625","target":"record","created_at":"2026-07-05T05:10:22Z","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":"2c73f99a9462fed963f3e4583c06fd9d09a9855d1913658d5c34dee8f18c0b68","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-25T05:12:47Z","title_canon_sha256":"4f2ff66906d792fa9ba74d31f21675aef23ee16f23cb860f5da0f609a6490572"},"schema_version":"1.0","source":{"id":"2210.13771","kind":"arxiv","version":1}},"canonical_sha256":"f4ef0e5d1ab4d462154f0ac607e0447325dbcc82739ca69a7fa6907f5d9363f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4ef0e5d1ab4d462154f0ac607e0447325dbcc82739ca69a7fa6907f5d9363f0","first_computed_at":"2026-07-05T05:10:22.287245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:22.287245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Od2j4xwSddRY9xtor9T0mAOL8DATmtheOg90k802/o5pJiJArapj1vADw783xQ+I/8P+stP5mqD3GSSEXIdLBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:22.287842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e943324228663a8e39e2dbf463954d776bae5a7cb2eb96ff7cb95b1ba2352625","sha256:9313aeb9aeb57c120479d7003fb4b659a42bbcefba1c559f8e26c82b316a2918"],"state_sha256":"ed893224d32b5274c3dfc377f9f889c7055f4b0e5564ece44468f28636e86f22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MtzdBYGArUoaSzuox9xBv9RJ40Ep5cfATGeqnCeQsX+87nS7dO4V/KLCHYd9v5S5lcNUG6DrxmjuZHwwoqSdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:37:07.151582Z","bundle_sha256":"f9dd2b69dcda9d44a2acc25d71a1df4fc973e19b3ac4120a9c7051fb9da7b42d"}}