{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FTD7BVHPURSHPJGOPLUEFR5W7H","short_pith_number":"pith:FTD7BVHP","schema_version":"1.0","canonical_sha256":"2cc7f0d4efa46477a4ce7ae842c7b6f9e490f8ae9ab187abb9dde3956f4b0cf8","source":{"kind":"arxiv","id":"1609.03499","version":2},"attestation_state":"computed","paper":{"title":"WaveNet: A Generative Model for Raw Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"WaveNet generates raw audio waveforms by predicting each sample from all previous ones and yields more natural text-to-speech than prior systems.","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Aaron van den Oord, Alex Graves, Andrew Senior, Heiga Zen, Karen Simonyan, Koray Kavukcuoglu, Nal Kalchbrenner, Oriol Vinyals, Sander Dieleman","submitted_at":"2016-09-12T17:29:40Z","abstract_excerpt":"This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones; nonetheless we show that it can be efficiently trained on data with tens of thousands of samples per second of audio. When applied to text-to-speech, it yields state-of-the-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin. A single WaveNet can captur"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"1609.03499","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2016-09-12T17:29:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d37eeeb8476318de01ce3bec1fd40de17d70bf9e4d3a9d31e1137e341742445","abstract_canon_sha256":"380f5fa5f82ba1fede626c4be26bc5009cbd1223c74641fe4362f0c2c2d241c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T21:24:19.547470Z","signature_b64":"iiT2OgBQRhVzrkWy+6uFBOPgyL+tLYyyGGdi8Vjje2D0XiTBEqkK+VDEYV4J2QQ0bigFDkcZlvYRHL1emUC6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cc7f0d4efa46477a4ce7ae842c7b6f9e490f8ae9ab187abb9dde3956f4b0cf8","last_reissued_at":"2026-07-04T21:24:19.546961Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T21:24:19.546961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveNet: A Generative Model for Raw Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"WaveNet generates raw audio waveforms by predicting each sample from all previous ones and yields more natural text-to-speech than prior systems.","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Aaron van den Oord, Alex Graves, Andrew Senior, Heiga Zen, Karen Simonyan, Koray Kavukcuoglu, Nal Kalchbrenner, Oriol Vinyals, Sander Dieleman","submitted_at":"2016-09-12T17:29:40Z","abstract_excerpt":"This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones; nonetheless we show that it can be efficiently trained on data with tens of thousands of samples per second of audio. When applied to text-to-speech, it yields state-of-the-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin. A single WaveNet can captur"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When applied to text-to-speech, it yields state-of-the-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that human listener ratings of naturalness provide a reliable and unbiased measure of model quality, and that the autoregressive conditioning on prior samples plus speaker identity suffices to capture speaker characteristics without further mechanisms.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WaveNet generates realistic raw audio using an autoregressive neural network with dilated convolutions, achieving state-of-the-art naturalness in speech synthesis for English and Mandarin.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"WaveNet generates raw audio waveforms by predicting each sample from all previous ones and yields more natural text-to-speech than prior systems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ba7dd9419d135932cb469e7c957215415d0865d61dc54c69c33bc51dc3acdbb0"},"source":{"id":"1609.03499","kind":"arxiv","version":2},"verdict":{"id":"83a3d83a-2c58-40ac-b382-20b408abe767","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T20:23:22.651711Z","strongest_claim":"When applied to text-to-speech, it yields state-of-the-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin.","one_line_summary":"WaveNet generates realistic raw audio using an autoregressive neural network with dilated convolutions, achieving state-of-the-art naturalness in speech synthesis for English and Mandarin.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that human listener ratings of naturalness provide a reliable and unbiased measure of model quality, and that the autoregressive conditioning on prior samples plus speaker identity suffices to capture speaker characteristics without further mechanisms.","pith_extraction_headline":"WaveNet generates raw audio waveforms by predicting each sample from all previous ones and yields more natural text-to-speech than prior systems."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1609.03499/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":60,"sample":[{"doi":"","year":2015,"title":"Vocaine the vocoder and applications is speech synthesis","work_id":"13476cf6-ab84-4f09-8aa9-f713544d7c30","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1994,"title":"Mixture density networks","work_id":"c96b52e8-1df3-465c-9ee1-c4f716c37066","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","work_id":"d2a48269-aa6d-452f-895c-aafd2ec1f435","ref_index":3,"cited_arxiv_id":"1412.7062","is_internal_anchor":false},{"doi":"","year":1942,"title":"The Vowel: I ts Nature and Structure","work_id":"711ccdf7-1189-439b-b389-16643b375e61","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1939,"title":"Remaking speech","work_id":"320464ee-11c6-44a3-9c4e-2960841e1a5e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"78f1bca38f6ca865264d250c59a67b5ed8dffd6cfc250c611e8e51e27d0f01e0","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1521357bb85baf8caaf186adc4e4b3e61fa30c32cfca2574349b0cef7c6fae4b"},"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":"1609.03499","created_at":"2026-07-04T21:24:19.547021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.03499v2","created_at":"2026-07-04T21:24:19.547021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03499","created_at":"2026-07-04T21:24:19.547021+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTD7BVHPURSH","created_at":"2026-07-04T21:24:19.547021+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTD7BVHPURSHPJGO","created_at":"2026-07-04T21:24:19.547021+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTD7BVHP","created_at":"2026-07-04T21:24:19.547021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":86,"internal_anchor_count":86,"sample":[{"citing_arxiv_id":"2606.20518","citing_title":"FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20561","citing_title":"TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living","ref_index":203,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11746","citing_title":"Time Series Analysis in Machine Learning","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11184","citing_title":"TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10246","citing_title":"Linguistically Augmented Audio Speech Data (LinguAS)","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05911","citing_title":"DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04776","citing_title":"SoftPINCH: EMG-Driven Soft Exoskeleton Assistance for Finger Flexion and Grasping","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03825","citing_title":"Dynamic Short Convolutions Improve Transformers","ref_index":178,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02341","citing_title":"Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27644","citing_title":"CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28560","citing_title":"Depth-Staggered Fibonacci Spacing for Sparse Attention: Static Schedules Beat Learned Dilation and Extrapolate Where Dense Attention Fails","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30356","citing_title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30580","citing_title":"MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25413","citing_title":"Autoregression-Free Neural Operators for Time-Dependent PDEs","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27113","citing_title":"High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26624","citing_title":"MSCGC-KAN: Multi-scale Causal Graph Convolution and Kolmogorov-Arnold Feature Mapping for EEG Emotion Recognition","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.16488","citing_title":"An Energy-Driven Framework for Privacy-Aware Synthetic Data Generation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.28507","citing_title":"Universal Time Series Generation with Neural Controlled Differential Equations","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29713","citing_title":"The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29675","citing_title":"From Prompts to Context: An Ontology-Driven Framework for Human-Generative AI Collaboration","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1906.08977","citing_title":"Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10859","citing_title":"End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11645","citing_title":"RUSLAN: Russian Spoken Language Corpus for Speech Synthesis","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H","json":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H.json","graph_json":"https://pith.science/api/pith-number/FTD7BVHPURSHPJGOPLUEFR5W7H/graph.json","events_json":"https://pith.science/api/pith-number/FTD7BVHPURSHPJGOPLUEFR5W7H/events.json","paper":"https://pith.science/paper/FTD7BVHP"},"agent_actions":{"view_html":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H","download_json":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H.json","view_paper":"https://pith.science/paper/FTD7BVHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.03499&json=true","fetch_graph":"https://pith.science/api/pith-number/FTD7BVHPURSHPJGOPLUEFR5W7H/graph.json","fetch_events":"https://pith.science/api/pith-number/FTD7BVHPURSHPJGOPLUEFR5W7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H/action/storage_attestation","attest_author":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H/action/author_attestation","sign_citation":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H/action/citation_signature","submit_replication":"https://pith.science/pith/FTD7BVHPURSHPJGOPLUEFR5W7H/action/replication_record"}},"created_at":"2026-07-04T21:24:19.547021+00:00","updated_at":"2026-07-04T21:24:19.547021+00:00"}