{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JCHDPSN32SQI64DHVG4ZLPUCNZ","short_pith_number":"pith:JCHDPSN3","schema_version":"1.0","canonical_sha256":"488e37c9bbd4a08f7067a9b995be826e6a89bf3709cc839725b629b3cd1fe77c","source":{"kind":"arxiv","id":"2204.00768","version":4},"attestation_state":"computed","paper":{"title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2022-04-02T05:28:48Z","abstract_excerpt":"The mainstream neural text-to-speech(TTS) pipeline is a cascade system, including an acoustic model(AM) that predicts acoustic feature from the input transcript and a vocoder that generates waveform according to the given acoustic feature. However, the acoustic feature in current TTS systems is typically mel-spectrogram, which is highly correlated along both time and frequency axes in a complicated way, leading to a great difficulty for the AM to predict. Although high-fidelity audio can be generated by recent neural vocoders from ground-truth(GT) mel-spectrogram, the gap between the GT and th"},"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":"2204.00768","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-04-02T05:28:48Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1d97380d4668253a28ea0d43d139e3a885eae6a862314adff23c8735207312ef","abstract_canon_sha256":"69a8202121c7b42889d02a94374fe8244e197fd7cafa908104e22d15748d365e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:49.466034Z","signature_b64":"X+zGq9eSgntwxpFBQICFLXiVxEu/oplRcetHoZwSPBvBJ8AxfBPzHGBCUhuMyDYSQ5m9s4G6hHHYZj5O8AaUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488e37c9bbd4a08f7067a9b995be826e6a89bf3709cc839725b629b3cd1fe77c","last_reissued_at":"2026-07-05T09:24:49.465535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:49.465535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2022-04-02T05:28:48Z","abstract_excerpt":"The mainstream neural text-to-speech(TTS) pipeline is a cascade system, including an acoustic model(AM) that predicts acoustic feature from the input transcript and a vocoder that generates waveform according to the given acoustic feature. However, the acoustic feature in current TTS systems is typically mel-spectrogram, which is highly correlated along both time and frequency axes in a complicated way, leading to a great difficulty for the AM to predict. Although high-fidelity audio can be generated by recent neural vocoders from ground-truth(GT) mel-spectrogram, the gap between the GT and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00768","kind":"arxiv","version":4},"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/2204.00768/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":"2204.00768","created_at":"2026-07-05T09:24:49.465593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00768v4","created_at":"2026-07-05T09:24:49.465593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00768","created_at":"2026-07-05T09:24:49.465593+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCHDPSN32SQI","created_at":"2026-07-05T09:24:49.465593+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCHDPSN32SQI64DH","created_at":"2026-07-05T09:24:49.465593+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCHDPSN3","created_at":"2026-07-05T09:24:49.465593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14202","citing_title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ","json":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ.json","graph_json":"https://pith.science/api/pith-number/JCHDPSN32SQI64DHVG4ZLPUCNZ/graph.json","events_json":"https://pith.science/api/pith-number/JCHDPSN32SQI64DHVG4ZLPUCNZ/events.json","paper":"https://pith.science/paper/JCHDPSN3"},"agent_actions":{"view_html":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ","download_json":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ.json","view_paper":"https://pith.science/paper/JCHDPSN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00768&json=true","fetch_graph":"https://pith.science/api/pith-number/JCHDPSN32SQI64DHVG4ZLPUCNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JCHDPSN32SQI64DHVG4ZLPUCNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ/action/storage_attestation","attest_author":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ/action/author_attestation","sign_citation":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ/action/citation_signature","submit_replication":"https://pith.science/pith/JCHDPSN32SQI64DHVG4ZLPUCNZ/action/replication_record"}},"created_at":"2026-07-05T09:24:49.465593+00:00","updated_at":"2026-07-05T09:24:49.465593+00:00"}