{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZJZWXXVDTNNAUXH6NTY2QYDBA5","short_pith_number":"pith:ZJZWXXVD","schema_version":"1.0","canonical_sha256":"ca736bdea39b5a0a5cfe6cf1a86061076825a95d69c64d86b34832bfe6dbb289","source":{"kind":"arxiv","id":"2203.16852","version":2},"attestation_state":"computed","paper":{"title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dan Lim, Eesung Kim, Sunghee Jung","submitted_at":"2022-03-31T07:25:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.16852","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-31T07:25:11Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"f4952ba635429a37a69cf56f9a69025669286ae5145f88ce92b2db8195b84b62","abstract_canon_sha256":"15daff477371810e215d39f2a8b2b413fc006f3bd38e3527c93011c67f52cda2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:48.223423Z","signature_b64":"f6J9ovtNGoTPMAGD34sY9TjmsbcmNk1IFmqTUktcFSl9yrSkqvKYIEcN/+pOA1UfUe6FzNXgEncjH9XcuHLhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca736bdea39b5a0a5cfe6cf1a86061076825a95d69c64d86b34832bfe6dbb289","last_reissued_at":"2026-07-05T04:36:48.222925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:48.222925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dan Lim, Eesung Kim, Sunghee Jung","submitted_at":"2022-03-31T07:25:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16852","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.16852/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.16852","created_at":"2026-07-05T04:36:48.222987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16852v2","created_at":"2026-07-05T04:36:48.222987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16852","created_at":"2026-07-05T04:36:48.222987+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJZWXXVDTNNA","created_at":"2026-07-05T04:36:48.222987+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJZWXXVDTNNAUXH6","created_at":"2026-07-05T04:36:48.222987+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJZWXXVD","created_at":"2026-07-05T04:36:48.222987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5","json":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5.json","graph_json":"https://pith.science/api/pith-number/ZJZWXXVDTNNAUXH6NTY2QYDBA5/graph.json","events_json":"https://pith.science/api/pith-number/ZJZWXXVDTNNAUXH6NTY2QYDBA5/events.json","paper":"https://pith.science/paper/ZJZWXXVD"},"agent_actions":{"view_html":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5","download_json":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5.json","view_paper":"https://pith.science/paper/ZJZWXXVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16852&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJZWXXVDTNNAUXH6NTY2QYDBA5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJZWXXVDTNNAUXH6NTY2QYDBA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5/action/storage_attestation","attest_author":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5/action/author_attestation","sign_citation":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5/action/citation_signature","submit_replication":"https://pith.science/pith/ZJZWXXVDTNNAUXH6NTY2QYDBA5/action/replication_record"}},"created_at":"2026-07-05T04:36:48.222987+00:00","updated_at":"2026-07-05T04:36:48.222987+00:00"}