{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:E4SNF44QOWMJRKYTIVQ7WJ7QQE","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":"26abbed34cabcd209a2ef26701ba5543b7b272c3110ed27e563ea2f5594b0fb2","cross_cats_sorted":["cs.CL","cs.LG","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T16:50:51Z","title_canon_sha256":"a5be49861ab9bf40131a71203e9a18d8014abe58b15e9abf286690bc89ad588b"},"schema_version":"1.0","source":{"id":"2106.15561","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15561","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15561v3","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15561","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"E4SNF44QOWMJ","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"E4SNF44QOWMJRKYT","created_at":"2026-07-05T03:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"E4SNF44Q","created_at":"2026-07-05T03:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:a55baddfa22a708c1872017d517911e1ae57c2dcd9f5672f4b49b7492af4be71","target":"graph","created_at":"2026-07-05T03:00:09Z","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/2106.15561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including ","authors_text":"Frank Soong, Tao Qin, Tie-Yan Liu, Xu Tan","cross_cats":["cs.CL","cs.LG","cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T16:50:51Z","title":"A Survey on Neural Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15561","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":"sha256:0a1618c54116c6c1694e94cdf6cac8cf506f899d6007f32f67fac759dc1b382a","target":"record","created_at":"2026-07-05T03:00:09Z","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":"26abbed34cabcd209a2ef26701ba5543b7b272c3110ed27e563ea2f5594b0fb2","cross_cats_sorted":["cs.CL","cs.LG","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T16:50:51Z","title_canon_sha256":"a5be49861ab9bf40131a71203e9a18d8014abe58b15e9abf286690bc89ad588b"},"schema_version":"1.0","source":{"id":"2106.15561","kind":"arxiv","version":3}},"canonical_sha256":"2724d2f390759898ab134561fb27f0811f4b495b44a35f42436c8a983b613a72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2724d2f390759898ab134561fb27f0811f4b495b44a35f42436c8a983b613a72","first_computed_at":"2026-07-05T03:00:09.966542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:09.966542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ScTEyBjYqBlQ5z/EqVEVUUhhFMQJLV8iJnDq4f2nd/tZhV7NgFPebcV3qpYWSHyMLNaqT42FdHFffEHeGEW1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:09.967010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15561","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a1618c54116c6c1694e94cdf6cac8cf506f899d6007f32f67fac759dc1b382a","sha256:a55baddfa22a708c1872017d517911e1ae57c2dcd9f5672f4b49b7492af4be71"],"state_sha256":"4763be7ba307a74baadf7766b70b35866686d7cb26c7409b7568b7291700908d"}