{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:74RFC6PLACZGPYZFZZ34MKPXB4","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":"f5989a7c0fa257a1453ba149b1c20de360a053c5c6953849e5db3502c92ab97a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-09T16:57:35Z","title_canon_sha256":"34326d2b933745e8988c1e09aab2a5881dafc937e5935899f09625ad4d3dd5b5"},"schema_version":"1.0","source":{"id":"2205.04421","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.04421","created_at":"2026-07-05T04:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2205.04421v2","created_at":"2026-07-05T04:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04421","created_at":"2026-07-05T04:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"74RFC6PLACZG","created_at":"2026-07-05T04:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"74RFC6PLACZGPYZF","created_at":"2026-07-05T04:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"74RFC6PL","created_at":"2026-07-05T04:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:4f80538f3d9b35120692efd88101b01ffd5b8516dea0239e45f98cfcea5f76a2","target":"graph","created_at":"2026-07-05T04:22:09Z","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/2205.04421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text to speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge that quality and how to achieve it. In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset. Specifically, we leverage a variational autoencoder (VA","authors_text":"Chen Zhang, Frank Soong, Haohe Liu, Jian Cong, Jiawei Chen, Lei He, Sheng Zhao, Tao Qin, Tie-Yan Liu, Xi Wang, Xu Tan, Yanqing Liu, Yichong Leng, Yuanhao Yi","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-09T16:57:35Z","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04421","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:eaaae22aceb746c69155dd8a9c7fb87c7f17970e96a872696df8971ed9f79981","target":"record","created_at":"2026-07-05T04:22:09Z","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":"f5989a7c0fa257a1453ba149b1c20de360a053c5c6953849e5db3502c92ab97a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-09T16:57:35Z","title_canon_sha256":"34326d2b933745e8988c1e09aab2a5881dafc937e5935899f09625ad4d3dd5b5"},"schema_version":"1.0","source":{"id":"2205.04421","kind":"arxiv","version":2}},"canonical_sha256":"ff225179eb00b267e325ce77c629f70f1564e86444b74f2349c82a923815e7be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff225179eb00b267e325ce77c629f70f1564e86444b74f2349c82a923815e7be","first_computed_at":"2026-07-05T04:22:09.069899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:09.069899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2q/gvO8Ia5tuaL8gm3nl5mwwiJV0EPP7lWHW5P1Rgnqep/lpGfC18A9LBiU/uL5bj7t2ZuI2JQjTl3rn+YWMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:09.070518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.04421","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaaae22aceb746c69155dd8a9c7fb87c7f17970e96a872696df8971ed9f79981","sha256:4f80538f3d9b35120692efd88101b01ffd5b8516dea0239e45f98cfcea5f76a2"],"state_sha256":"f1fe7d94719bb686e345d6a620b9cc92c31eb4f33d662c2597e4c3b043599f4e"}