{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YDEMNCIWDTFZ7UTJRN4MC63Q5V","short_pith_number":"pith:YDEMNCIW","schema_version":"1.0","canonical_sha256":"c0c8c689161ccb9fd2698b78c17b70ed6cbaaa97ed6ddd7db0e32156a031d8cd","source":{"kind":"arxiv","id":"1807.07281","version":3},"attestation_state":"computed","paper":{"title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jitong Chen, Kainan Peng, Wei Ping","submitted_at":"2018-07-19T08:15:41Z","abstract_excerpt":"In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a regularized KL divergence between their highly-peaked output distributions. Our method computes the KL divergence in closed-form, which simplifies the training algorithm and provides very efficient distillation. In addition, we introduce the first text-to-wave neural architecture for speech synthesis, which is fully convolutional and enables fast end-to-end "},"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":"1807.07281","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-19T08:15:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"27cf47604a63d4181e8c4953027686fa72e838517c6f8cba643fc9bcddf0c34d","abstract_canon_sha256":"9779cbe7149a23a77ff12115b8b078bc426cb3bab7b95b0ad975092bb871c888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:59.022546Z","signature_b64":"tIVD9XURzngAgixiYKu5ufDaNA3xfMZnxvhNlog9knHH5mvMT1Hhn2yCNnIHF+2gLkTlfEQ4kYobIIgwE3UtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0c8c689161ccb9fd2698b78c17b70ed6cbaaa97ed6ddd7db0e32156a031d8cd","last_reissued_at":"2026-05-17T23:52:59.021842Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:59.021842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jitong Chen, Kainan Peng, Wei Ping","submitted_at":"2018-07-19T08:15:41Z","abstract_excerpt":"In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a regularized KL divergence between their highly-peaked output distributions. Our method computes the KL divergence in closed-form, which simplifies the training algorithm and provides very efficient distillation. In addition, we introduce the first text-to-wave neural architecture for speech synthesis, which is fully convolutional and enables fast end-to-end "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07281","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1807.07281","created_at":"2026-05-17T23:52:59.021945+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.07281v3","created_at":"2026-05-17T23:52:59.021945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07281","created_at":"2026-05-17T23:52:59.021945+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDEMNCIWDTFZ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDEMNCIWDTFZ7UTJ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDEMNCIW","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10859","citing_title":"End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V","json":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V.json","graph_json":"https://pith.science/api/pith-number/YDEMNCIWDTFZ7UTJRN4MC63Q5V/graph.json","events_json":"https://pith.science/api/pith-number/YDEMNCIWDTFZ7UTJRN4MC63Q5V/events.json","paper":"https://pith.science/paper/YDEMNCIW"},"agent_actions":{"view_html":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V","download_json":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V.json","view_paper":"https://pith.science/paper/YDEMNCIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.07281&json=true","fetch_graph":"https://pith.science/api/pith-number/YDEMNCIWDTFZ7UTJRN4MC63Q5V/graph.json","fetch_events":"https://pith.science/api/pith-number/YDEMNCIWDTFZ7UTJRN4MC63Q5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V/action/storage_attestation","attest_author":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V/action/author_attestation","sign_citation":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V/action/citation_signature","submit_replication":"https://pith.science/pith/YDEMNCIWDTFZ7UTJRN4MC63Q5V/action/replication_record"}},"created_at":"2026-05-17T23:52:59.021945+00:00","updated_at":"2026-05-17T23:52:59.021945+00:00"}