{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZJZWXXVDTNNAUXH6NTY2QYDBA5","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":"15daff477371810e215d39f2a8b2b413fc006f3bd38e3527c93011c67f52cda2","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-31T07:25:11Z","title_canon_sha256":"f4952ba635429a37a69cf56f9a69025669286ae5145f88ce92b2db8195b84b62"},"schema_version":"1.0","source":{"id":"2203.16852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16852","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16852v2","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16852","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZJZWXXVDTNNA","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZJZWXXVDTNNAUXH6","created_at":"2026-07-05T04:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZJZWXXVD","created_at":"2026-07-05T04:36:48Z"}],"graph_snapshots":[{"event_id":"sha256:6fcd67a3f0e068a762035d6cb97ded2e0f288b5f8c27904559588bd6ef433052","target":"graph","created_at":"2026-07-05T04:36:48Z","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/2203.16852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In neural text-to-speech (TTS), two-stage system or a cascade of separately learned models have shown synthesis quality close to human speech. For example, FastSpeech2 transforms an input text to a mel-spectrogram and then HiFi-GAN generates a raw waveform from a mel-spectogram where they are called an acoustic feature generator and a neural vocoder respectively. However, their training pipeline is somewhat cumbersome in that it requires a fine-tuning and an accurate speech-text alignment for optimal performance. In this work, we present end-to-end text-to-speech (E2E-TTS) model which has a si","authors_text":"Dan Lim, Eesung Kim, Sunghee Jung","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-31T07:25:11Z","title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16852","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":"sha256:233b3b0f1487d01d63f4a81c7f5bc5f78d9cde6bacb2280eb3071a718f7d0d7e","target":"record","created_at":"2026-07-05T04:36:48Z","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":"15daff477371810e215d39f2a8b2b413fc006f3bd38e3527c93011c67f52cda2","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-31T07:25:11Z","title_canon_sha256":"f4952ba635429a37a69cf56f9a69025669286ae5145f88ce92b2db8195b84b62"},"schema_version":"1.0","source":{"id":"2203.16852","kind":"arxiv","version":2}},"canonical_sha256":"ca736bdea39b5a0a5cfe6cf1a86061076825a95d69c64d86b34832bfe6dbb289","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca736bdea39b5a0a5cfe6cf1a86061076825a95d69c64d86b34832bfe6dbb289","first_computed_at":"2026-07-05T04:36:48.222925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:48.222925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f6J9ovtNGoTPMAGD34sY9TjmsbcmNk1IFmqTUktcFSl9yrSkqvKYIEcN/+pOA1UfUe6FzNXgEncjH9XcuHLhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:48.223423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:233b3b0f1487d01d63f4a81c7f5bc5f78d9cde6bacb2280eb3071a718f7d0d7e","sha256:6fcd67a3f0e068a762035d6cb97ded2e0f288b5f8c27904559588bd6ef433052"],"state_sha256":"aab9cda4e9c44c7c6b9ae24e3729cd153cf6a6ec839264e509040d6f3d56028a"}