{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PZTIQX22WGEVLXWLCJLPZRTY6D","short_pith_number":"pith:PZTIQX22","schema_version":"1.0","canonical_sha256":"7e66885f5ab18955decb1256fcc678f0d263c22411148706c79cfbfb38b51792","source":{"kind":"arxiv","id":"2207.04646","version":1},"attestation_state":"computed","paper":{"title":"DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Lei He, Ruiqing Xue, Sheng Zhao, Xu Tan, Yanqing Liu","submitted_at":"2022-07-11T06:15:45Z","abstract_excerpt":"Current text to speech (TTS) systems usually leverage a cascaded acoustic model and vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer from two limitations: 1) the acoustic model and vocoder are separately trained instead of jointly optimized, which incurs cascaded errors; 2) the intermediate speech representations (e.g., mel-spectrogram) are pre-designed and lose phase information, which are sub-optimal. To solve these problems, in this paper, we develop DelightfulTTS 2, a new end-to-end speech synthesis system with automatically learned speech representa"},"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":"2207.04646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-11T06:15:45Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"da84caab790fb3c5b3a40d51878475171c6165f401606d70e22356bb8eaca291","abstract_canon_sha256":"d0a2af533bf1e48ad96cae88cc977626b69d6f6a11143327d23dbc9422313d39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:01.591208Z","signature_b64":"EG++ab7AOzRKWkmJkEqie4imD5BzIUuB4abwWkSsHHGlTrIihAk+gGpdg0SeT7mYidT170HcpC4W3ZW9ar6CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e66885f5ab18955decb1256fcc678f0d263c22411148706c79cfbfb38b51792","last_reissued_at":"2026-07-05T04:39:01.590732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:01.590732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Lei He, Ruiqing Xue, Sheng Zhao, Xu Tan, Yanqing Liu","submitted_at":"2022-07-11T06:15:45Z","abstract_excerpt":"Current text to speech (TTS) systems usually leverage a cascaded acoustic model and vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer from two limitations: 1) the acoustic model and vocoder are separately trained instead of jointly optimized, which incurs cascaded errors; 2) the intermediate speech representations (e.g., mel-spectrogram) are pre-designed and lose phase information, which are sub-optimal. To solve these problems, in this paper, we develop DelightfulTTS 2, a new end-to-end speech synthesis system with automatically learned speech representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04646","kind":"arxiv","version":1},"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/2207.04646/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":"2207.04646","created_at":"2026-07-05T04:39:01.590791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04646v1","created_at":"2026-07-05T04:39:01.590791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04646","created_at":"2026-07-05T04:39:01.590791+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZTIQX22WGEV","created_at":"2026-07-05T04:39:01.590791+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZTIQX22WGEVLXWL","created_at":"2026-07-05T04:39:01.590791+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZTIQX22","created_at":"2026-07-05T04:39:01.590791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22746","citing_title":"Next Tokens Denoising for Speech Synthesis","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D","json":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D.json","graph_json":"https://pith.science/api/pith-number/PZTIQX22WGEVLXWLCJLPZRTY6D/graph.json","events_json":"https://pith.science/api/pith-number/PZTIQX22WGEVLXWLCJLPZRTY6D/events.json","paper":"https://pith.science/paper/PZTIQX22"},"agent_actions":{"view_html":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D","download_json":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D.json","view_paper":"https://pith.science/paper/PZTIQX22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04646&json=true","fetch_graph":"https://pith.science/api/pith-number/PZTIQX22WGEVLXWLCJLPZRTY6D/graph.json","fetch_events":"https://pith.science/api/pith-number/PZTIQX22WGEVLXWLCJLPZRTY6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D/action/storage_attestation","attest_author":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D/action/author_attestation","sign_citation":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D/action/citation_signature","submit_replication":"https://pith.science/pith/PZTIQX22WGEVLXWLCJLPZRTY6D/action/replication_record"}},"created_at":"2026-07-05T04:39:01.590791+00:00","updated_at":"2026-07-05T04:39:01.590791+00:00"}