{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6RTWWPDL2K6FQH4C5LO4FIP6JP","short_pith_number":"pith:6RTWWPDL","schema_version":"1.0","canonical_sha256":"f4676b3c6bd2bc581f82eaddc2a1fe4bd658769dd6d9ea9fc72a73044b809e9b","source":{"kind":"arxiv","id":"2202.13066","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Over-Smoothness in Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Tao Qin, Tie-Yan Liu, Xu Tan, Yi Ren, Zhou Zhao","submitted_at":"2022-02-26T05:22:32Z","abstract_excerpt":"Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency domains while generating speech mel-spectrograms, and thus cause blurry and over-smoothed results. In this work, we revisit this over-smoothing problem from a novel perspective: the degree of over-smoothness is determined by the gap between the complexity of data distributions and the capability of modeling methods. Both simplifying data distributions and im"},"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":"2202.13066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-26T05:22:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"217434bafec70b1becb0dd9fab909dd5e51e8f0b95c22755d0fa442c32ab4e31","abstract_canon_sha256":"fd5ede096eece2bfba7ea52edbde083c17b0fb0c3d8b3c83ea58a0632b4b945e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:25.699101Z","signature_b64":"XQFHpJjPBF2nSMct+d25C/aG0SbtAMUnmDj1yfH7ibinAsGRRbCMD5pjTLnKUmD0aZwe+n8bp9jclb/n0QYqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4676b3c6bd2bc581f82eaddc2a1fe4bd658769dd6d9ea9fc72a73044b809e9b","last_reissued_at":"2026-07-05T04:00:25.698614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:25.698614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Over-Smoothness in Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Tao Qin, Tie-Yan Liu, Xu Tan, Yi Ren, Zhou Zhao","submitted_at":"2022-02-26T05:22:32Z","abstract_excerpt":"Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency domains while generating speech mel-spectrograms, and thus cause blurry and over-smoothed results. In this work, we revisit this over-smoothing problem from a novel perspective: the degree of over-smoothness is determined by the gap between the complexity of data distributions and the capability of modeling methods. Both simplifying data distributions and im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13066","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/2202.13066/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":"2202.13066","created_at":"2026-07-05T04:00:25.698672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13066v1","created_at":"2026-07-05T04:00:25.698672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13066","created_at":"2026-07-05T04:00:25.698672+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RTWWPDL2K6F","created_at":"2026-07-05T04:00:25.698672+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RTWWPDL2K6FQH4C","created_at":"2026-07-05T04:00:25.698672+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RTWWPDL","created_at":"2026-07-05T04:00:25.698672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13053","citing_title":"ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP","json":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP.json","graph_json":"https://pith.science/api/pith-number/6RTWWPDL2K6FQH4C5LO4FIP6JP/graph.json","events_json":"https://pith.science/api/pith-number/6RTWWPDL2K6FQH4C5LO4FIP6JP/events.json","paper":"https://pith.science/paper/6RTWWPDL"},"agent_actions":{"view_html":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP","download_json":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP.json","view_paper":"https://pith.science/paper/6RTWWPDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13066&json=true","fetch_graph":"https://pith.science/api/pith-number/6RTWWPDL2K6FQH4C5LO4FIP6JP/graph.json","fetch_events":"https://pith.science/api/pith-number/6RTWWPDL2K6FQH4C5LO4FIP6JP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP/action/storage_attestation","attest_author":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP/action/author_attestation","sign_citation":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP/action/citation_signature","submit_replication":"https://pith.science/pith/6RTWWPDL2K6FQH4C5LO4FIP6JP/action/replication_record"}},"created_at":"2026-07-05T04:00:25.698672+00:00","updated_at":"2026-07-05T04:00:25.698672+00:00"}