{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:72GQ7EXXBVOY652LMSCLS33HR3","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":"bc666c60ebfd3342a3ca230a5d8ab3346b7abf117dfbcc80c178f9e0e3c08738","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-01-30T00:53:50Z","title_canon_sha256":"27fb85ae5334dc23157a65677a30a994bc38ef2b393a1bb1138994abe3c0782e"},"schema_version":"1.0","source":{"id":"2301.12596","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12596","created_at":"2026-07-05T06:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12596v3","created_at":"2026-07-05T06:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12596","created_at":"2026-07-05T06:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"72GQ7EXXBVOY","created_at":"2026-07-05T06:14:40Z"},{"alias_kind":"pith_short_16","alias_value":"72GQ7EXXBVOY652L","created_at":"2026-07-05T06:14:40Z"},{"alias_kind":"pith_short_8","alias_value":"72GQ7EXX","created_at":"2026-07-05T06:14:40Z"}],"graph_snapshots":[{"event_id":"sha256:647fab2038914c34f4825ff7bbdc6a602a1ea0aa1165ae70b82b4b5e44e07f57","target":"graph","created_at":"2026-07-05T06:14:40Z","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/2301.12596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method for zero-shot multilingual TTS using text-only data for the target language. The use of text-only data allows the development of TTS systems for low-resource languages for which only textual resources are available, making TTS accessible to thousands of languages. Inspired by the strong cross-lingual transferability of multilingual language models, our frame","authors_text":"Hiroshi Saruwatari, Shinji Watanabe, Shinnosuke Takamichi, Soumi Maiti, Takaaki Saeki, Xinjian Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-01-30T00:53:50Z","title":"Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12596","kind":"arxiv","version":3},"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":"sha256:97e59eed01c10b3ff1487b7d35cdd850f3612edc575f4a31747f2378ec8198bb","target":"record","created_at":"2026-07-05T06:14:40Z","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":"bc666c60ebfd3342a3ca230a5d8ab3346b7abf117dfbcc80c178f9e0e3c08738","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-01-30T00:53:50Z","title_canon_sha256":"27fb85ae5334dc23157a65677a30a994bc38ef2b393a1bb1138994abe3c0782e"},"schema_version":"1.0","source":{"id":"2301.12596","kind":"arxiv","version":3}},"canonical_sha256":"fe8d0f92f70d5d8f774b6484b96f678edbcbd994c47833af81c4dfe807dca46f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe8d0f92f70d5d8f774b6484b96f678edbcbd994c47833af81c4dfe807dca46f","first_computed_at":"2026-07-05T06:14:40.012215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:40.012215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67jgWDnKmEJiWQ9IuSA38AG8K6YtN33gBr6YzGTtOTMHJs3bQnmZl9tKHwiJGiGoiGaUA5V6RUjvJ4M53vI9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:40.012649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12596","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97e59eed01c10b3ff1487b7d35cdd850f3612edc575f4a31747f2378ec8198bb","sha256:647fab2038914c34f4825ff7bbdc6a602a1ea0aa1165ae70b82b4b5e44e07f57"],"state_sha256":"6f5ba4a0b0d45ee542899fc98117acc81195971fa67f2f24f4c72e828d2b77e9"}