{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CP75ZZJAS44FWYDNQZY2676HOT","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":"0fc5705b9f96f2e209bebdd7eccb74db1f66228fcffa51a055db1222f7daaafd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T07:22:23Z","title_canon_sha256":"6992e7e5a1341949204c9b0ee1af3f2bd4affcca7845c1611902bb01155caeac"},"schema_version":"1.0","source":{"id":"2110.07187","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07187","created_at":"2026-07-05T03:23:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07187v2","created_at":"2026-07-05T03:23:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07187","created_at":"2026-07-05T03:23:15Z"},{"alias_kind":"pith_short_12","alias_value":"CP75ZZJAS44F","created_at":"2026-07-05T03:23:15Z"},{"alias_kind":"pith_short_16","alias_value":"CP75ZZJAS44FWYDN","created_at":"2026-07-05T03:23:15Z"},{"alias_kind":"pith_short_8","alias_value":"CP75ZZJA","created_at":"2026-07-05T03:23:15Z"}],"graph_snapshots":[{"event_id":"sha256:a4eeef226e3df3928d442d97a583ce380266b4aac676f1c9cfd891bbeac853ec","target":"graph","created_at":"2026-07-05T03:23:15Z","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/2110.07187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"International Phonetic Alphabet (IPA) has been widely used in cross-lingual text-to-speech (TTS) to achieve cross-lingual voice cloning (CL VC). However, IPA itself has been understudied in cross-lingual TTS. In this paper, we report some empirical findings of building a cross-lingual TTS model using IPA as inputs. Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance. Furthermore, we find that using a dataset including one speaker per language to build an IPA-based TTS system would fail CL VC since the language-unique IPA","authors_text":"Haitong Zhang, Haoyue Zhan, Xinyuan Yu, Yang Zhang, Yue Lin","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T07:22:23Z","title":"Revisiting IPA-based Cross-lingual Text-to-speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07187","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":"sha256:524d5d60914dbd1bed02b2dc16591b2468374e3d4e2e545e86ee51afc039319e","target":"record","created_at":"2026-07-05T03:23:15Z","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":"0fc5705b9f96f2e209bebdd7eccb74db1f66228fcffa51a055db1222f7daaafd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T07:22:23Z","title_canon_sha256":"6992e7e5a1341949204c9b0ee1af3f2bd4affcca7845c1611902bb01155caeac"},"schema_version":"1.0","source":{"id":"2110.07187","kind":"arxiv","version":2}},"canonical_sha256":"13ffdce52097385b606d8671af7fc774ea9670a9b05151e8a4c1f84240a87a34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13ffdce52097385b606d8671af7fc774ea9670a9b05151e8a4c1f84240a87a34","first_computed_at":"2026-07-05T03:23:15.494752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:15.494752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/72LWQ1iNC9lSPD9bbXBsFZepOXCyRTEWXQNCax23ybF+PNLF4oAxM3pyzWVIbwh3n1muL8xXzEeYGGUJd2bCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:15.495117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07187","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:524d5d60914dbd1bed02b2dc16591b2468374e3d4e2e545e86ee51afc039319e","sha256:a4eeef226e3df3928d442d97a583ce380266b4aac676f1c9cfd891bbeac853ec"],"state_sha256":"91d47f9f104c10a8c12098e1b3a94221c9cd4f19040d5fafee05d5f7f4d97e25"}