{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QQJ7EAEP24KMR5KMXS47M4OO43","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":"f2b8ddee352d1512b60920e27e58a65fa9abf15b420686fbd3aa67cc102b2802","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T01:07:12Z","title_canon_sha256":"05b79519faa0584a6746f8f625f21afea222a3758a03150a8ab4bb83c7c0f0e7"},"schema_version":"1.0","source":{"id":"2106.06103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06103","created_at":"2026-07-05T02:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06103v1","created_at":"2026-07-05T02:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06103","created_at":"2026-07-05T02:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"QQJ7EAEP24KM","created_at":"2026-07-05T02:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"QQJ7EAEP24KMR5KM","created_at":"2026-07-05T02:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"QQJ7EAEP","created_at":"2026-07-05T02:48:26Z"}],"graph_snapshots":[{"event_id":"sha256:3db1cc2405a5465a14ac8eb1ddf51b3caa22d30e70f3ac692fd66f86430c84e0","target":"graph","created_at":"2026-07-05T02:48:26Z","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/2106.06103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input","authors_text":"Jaehyeon Kim, Juhee Son, Jungil Kong","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T01:07:12Z","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06103","kind":"arxiv","version":1},"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":"sha256:6068015b720c024aff699a9a9629dfde573c6138d4eb229328ee9b838d998d6e","target":"record","created_at":"2026-07-05T02:48:26Z","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":"f2b8ddee352d1512b60920e27e58a65fa9abf15b420686fbd3aa67cc102b2802","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T01:07:12Z","title_canon_sha256":"05b79519faa0584a6746f8f625f21afea222a3758a03150a8ab4bb83c7c0f0e7"},"schema_version":"1.0","source":{"id":"2106.06103","kind":"arxiv","version":1}},"canonical_sha256":"8413f2008fd714c8f54cbcb9f671cee6da7be7f66971568e1bea1e174bfda8ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8413f2008fd714c8f54cbcb9f671cee6da7be7f66971568e1bea1e174bfda8ba","first_computed_at":"2026-07-05T02:48:26.077429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:26.077429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7wTlav7U+hEplm4Qv0JjhQuImf0O2i3PZE2rQRah4jLs9sOVPKJlLo5xE557R/790rBR4tRwEpgkZyIw95xrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:26.077969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6068015b720c024aff699a9a9629dfde573c6138d4eb229328ee9b838d998d6e","sha256:3db1cc2405a5465a14ac8eb1ddf51b3caa22d30e70f3ac692fd66f86430c84e0"],"state_sha256":"233aa8715d1a1da9ba672d8deb8e86b27ef012e38fdf3e37da85245b95bbcf02"}