{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3YQHX7HZ2S6X22OYBXF6SDD4IS","short_pith_number":"pith:3YQHX7HZ","schema_version":"1.0","canonical_sha256":"de207bfcf9d4bd7d69d80dcbe90c7c448b93983b038510498bb07cab57b2b3ec","source":{"kind":"arxiv","id":"1711.10433","version":1},"attestation_state":"computed","paper":{"title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron van den Oord, Alex Graves, Dan Belov, Demis Hassabis, Dominik Grewe, Edward Lockhart, Erich Elsen, Florian Stimberg, George van den Driessche, Heiga Zen, Helen King, Igor Babuschkin, Karen Simonyan, Koray Kavukcuoglu, Luis C. Cobo, Nal Kalchbrenner, Norman Casagrande, Oriol Vinyals, Sander Dieleman, Seb Noury, Tom Walters, Yazhe Li","submitted_at":"2017-11-28T17:48:11Z","abstract_excerpt":"The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. T"},"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":"1711.10433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T17:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"5763ea152e2415d7430b9239c82c30688e865d2abd6b4c5802dc15187c46489b","abstract_canon_sha256":"344c855ee1810e2d1440034b308e76e173927b324244c5ab753484cdcac9d048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:22.137389Z","signature_b64":"EwBqiRXmcxjLgPSS74hMhl2GjcOeaKCxzFdOD0r+Vseg96RFZNxjZSO2R58hA+oBKmaZw7H1j99OdX4cW6WgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de207bfcf9d4bd7d69d80dcbe90c7c448b93983b038510498bb07cab57b2b3ec","last_reissued_at":"2026-05-18T00:29:22.136771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:22.136771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron van den Oord, Alex Graves, Dan Belov, Demis Hassabis, Dominik Grewe, Edward Lockhart, Erich Elsen, Florian Stimberg, George van den Driessche, Heiga Zen, Helen King, Igor Babuschkin, Karen Simonyan, Koray Kavukcuoglu, Luis C. Cobo, Nal Kalchbrenner, Norman Casagrande, Oriol Vinyals, Sander Dieleman, Seb Noury, Tom Walters, Yazhe Li","submitted_at":"2017-11-28T17:48:11Z","abstract_excerpt":"The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10433","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":""},"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":"1711.10433","created_at":"2026-05-18T00:29:22.136881+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10433v1","created_at":"2026-05-18T00:29:22.136881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10433","created_at":"2026-05-18T00:29:22.136881+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YQHX7HZ2S6X","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YQHX7HZ2S6X22OY","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YQHX7HZ","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS","json":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS.json","graph_json":"https://pith.science/api/pith-number/3YQHX7HZ2S6X22OYBXF6SDD4IS/graph.json","events_json":"https://pith.science/api/pith-number/3YQHX7HZ2S6X22OYBXF6SDD4IS/events.json","paper":"https://pith.science/paper/3YQHX7HZ"},"agent_actions":{"view_html":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS","download_json":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS.json","view_paper":"https://pith.science/paper/3YQHX7HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10433&json=true","fetch_graph":"https://pith.science/api/pith-number/3YQHX7HZ2S6X22OYBXF6SDD4IS/graph.json","fetch_events":"https://pith.science/api/pith-number/3YQHX7HZ2S6X22OYBXF6SDD4IS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS/action/storage_attestation","attest_author":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS/action/author_attestation","sign_citation":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS/action/citation_signature","submit_replication":"https://pith.science/pith/3YQHX7HZ2S6X22OYBXF6SDD4IS/action/replication_record"}},"created_at":"2026-05-18T00:29:22.136881+00:00","updated_at":"2026-05-18T00:29:22.136881+00:00"}