{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2QJX7GUWTHIKE75TYXXMVCVVIQ","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":"de7e0cfc85e1fc69be099407415a8eb6dafbc59f9390594e12991a05a054a8a1","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-07T13:35:16Z","title_canon_sha256":"d93d0d95972c090f3501dc439b131499f74169ab5ae41611bacd880925a0e312"},"schema_version":"1.0","source":{"id":"2211.03545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03545","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03545v2","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03545","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"2QJX7GUWTHIK","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"2QJX7GUWTHIKE75T","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"2QJX7GUW","created_at":"2026-07-05T05:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:b9e53c207d94791fc2beb5c354b82d18cc50449c796c3604ec275e8c9482b4eb","target":"graph","created_at":"2026-07-05T05:22:12Z","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/2211.03545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks, including cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes given a speech example and its transcription. By learning to reconstruct the masked parts of the ","authors_text":"Chao Pang, He Bai, Hua Wu, Junkun Chen, Liang Huang, Pengfei Zhu, Renjie Zheng, Shuohuan Wang, Tian Yuan, Xiaoran Fan, Yu Sun, Zeyu Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-07T13:35:16Z","title":"ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03545","kind":"arxiv","version":2},"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":"sha256:9b8c000092e6e6d8dffe68951ecd271c2f66b840b8e39a44be3513be8a34b144","target":"record","created_at":"2026-07-05T05:22:12Z","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":"de7e0cfc85e1fc69be099407415a8eb6dafbc59f9390594e12991a05a054a8a1","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-07T13:35:16Z","title_canon_sha256":"d93d0d95972c090f3501dc439b131499f74169ab5ae41611bacd880925a0e312"},"schema_version":"1.0","source":{"id":"2211.03545","kind":"arxiv","version":2}},"canonical_sha256":"d4137f9a9699d0a27fb3c5eeca8ab5441a336baba58919054eef3993b85c5c7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4137f9a9699d0a27fb3c5eeca8ab5441a336baba58919054eef3993b85c5c7a","first_computed_at":"2026-07-05T05:22:12.256947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:12.256947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d/9uiFFFQVVMMZEUgFkz3aMc+3caVIMImmnHZJsctjz8EE2cNrMpg4mRX24rd4EQ+hlO/6iF02AwuMm2XDRhDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:12.257397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.03545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b8c000092e6e6d8dffe68951ecd271c2f66b840b8e39a44be3513be8a34b144","sha256:b9e53c207d94791fc2beb5c354b82d18cc50449c796c3604ec275e8c9482b4eb"],"state_sha256":"82194eb4c97bb969a4b89c1275148ac6e8c20ed3cb674a717175816716ae6e32"}