{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CP75ZZJAS44FWYDNQZY2676HOT","short_pith_number":"pith:CP75ZZJA","schema_version":"1.0","canonical_sha256":"13ffdce52097385b606d8671af7fc774ea9670a9b05151e8a4c1f84240a87a34","source":{"kind":"arxiv","id":"2110.07187","version":2},"attestation_state":"computed","paper":{"title":"Revisiting IPA-based Cross-lingual Text-to-speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haitong Zhang, Haoyue Zhan, Xinyuan Yu, Yang Zhang, Yue Lin","submitted_at":"2021-10-14T07:22:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.07187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T07:22:23Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6992e7e5a1341949204c9b0ee1af3f2bd4affcca7845c1611902bb01155caeac","abstract_canon_sha256":"0fc5705b9f96f2e209bebdd7eccb74db1f66228fcffa51a055db1222f7daaafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:15.495117Z","signature_b64":"/72LWQ1iNC9lSPD9bbXBsFZepOXCyRTEWXQNCax23ybF+PNLF4oAxM3pyzWVIbwh3n1muL8xXzEeYGGUJd2bCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13ffdce52097385b606d8671af7fc774ea9670a9b05151e8a4c1f84240a87a34","last_reissued_at":"2026-07-05T03:23:15.494752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:15.494752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting IPA-based Cross-lingual Text-to-speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haitong Zhang, Haoyue Zhan, Xinyuan Yu, Yang Zhang, Yue Lin","submitted_at":"2021-10-14T07:22:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07187","kind":"arxiv","version":2},"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/2110.07187/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.07187","created_at":"2026-07-05T03:23:15.494802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07187v2","created_at":"2026-07-05T03:23:15.494802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07187","created_at":"2026-07-05T03:23:15.494802+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP75ZZJAS44F","created_at":"2026-07-05T03:23:15.494802+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP75ZZJAS44FWYDN","created_at":"2026-07-05T03:23:15.494802+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP75ZZJA","created_at":"2026-07-05T03:23:15.494802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT","json":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT.json","graph_json":"https://pith.science/api/pith-number/CP75ZZJAS44FWYDNQZY2676HOT/graph.json","events_json":"https://pith.science/api/pith-number/CP75ZZJAS44FWYDNQZY2676HOT/events.json","paper":"https://pith.science/paper/CP75ZZJA"},"agent_actions":{"view_html":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT","download_json":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT.json","view_paper":"https://pith.science/paper/CP75ZZJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07187&json=true","fetch_graph":"https://pith.science/api/pith-number/CP75ZZJAS44FWYDNQZY2676HOT/graph.json","fetch_events":"https://pith.science/api/pith-number/CP75ZZJAS44FWYDNQZY2676HOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT/action/storage_attestation","attest_author":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT/action/author_attestation","sign_citation":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT/action/citation_signature","submit_replication":"https://pith.science/pith/CP75ZZJAS44FWYDNQZY2676HOT/action/replication_record"}},"created_at":"2026-07-05T03:23:15.494802+00:00","updated_at":"2026-07-05T03:23:15.494802+00:00"}