{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SHC65RYFPTWIAPIGPKNWMSANN7","short_pith_number":"pith:SHC65RYF","schema_version":"1.0","canonical_sha256":"91c5eec7057cec803d067a9b66480d6ff0f3e0782918ee91bef9831ed25a8e13","source":{"kind":"arxiv","id":"1802.08435","version":2},"attestation_state":"computed","paper":{"title":"Efficient Neural Audio Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron van den Oord, Edward Lockhart, Erich Elsen, Florian Stimberg, Karen Simonyan, Koray Kavukcuoglu, Nal Kalchbrenner, Norman Casagrande, Sander Dieleman, Seb Noury","submitted_at":"2018-02-23T08:20:23Z","abstract_excerpt":"Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however remained an elusive problem. With a focus on text-to-speech synthesis, we describe a set of general techniques for reducing sampling time while maintaining high output quality. We first describe a single-layer recurrent neural network, the WaveRNN, with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model. The compact form of the ne"},"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":"1802.08435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-02-23T08:20:23Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"0e4944bc135b9997a783022d80300f85245742b4142dfaa91499487d394176b1","abstract_canon_sha256":"e14855009eb7dadccf533ef770b6f89c8756b66395f3975538530036473dc8fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:24.518714Z","signature_b64":"XDwOu4RCfH2fqEB+oOYKF2IAA+gqU68836KDSBeMhhFFhYNIokH0+nauquaHTiop2kHI5UL5LMBo8EWnB4ynDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91c5eec7057cec803d067a9b66480d6ff0f3e0782918ee91bef9831ed25a8e13","last_reissued_at":"2026-05-18T00:12:24.518047Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:24.518047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Neural Audio Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron van den Oord, Edward Lockhart, Erich Elsen, Florian Stimberg, Karen Simonyan, Koray Kavukcuoglu, Nal Kalchbrenner, Norman Casagrande, Sander Dieleman, Seb Noury","submitted_at":"2018-02-23T08:20:23Z","abstract_excerpt":"Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however remained an elusive problem. With a focus on text-to-speech synthesis, we describe a set of general techniques for reducing sampling time while maintaining high output quality. We first describe a single-layer recurrent neural network, the WaveRNN, with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model. The compact form of the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08435","kind":"arxiv","version":2},"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":"1802.08435","created_at":"2026-05-18T00:12:24.518146+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08435v2","created_at":"2026-05-18T00:12:24.518146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08435","created_at":"2026-05-18T00:12:24.518146+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHC65RYFPTWI","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHC65RYFPTWIAPIG","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHC65RYF","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2202.08906","citing_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7","json":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7.json","graph_json":"https://pith.science/api/pith-number/SHC65RYFPTWIAPIGPKNWMSANN7/graph.json","events_json":"https://pith.science/api/pith-number/SHC65RYFPTWIAPIGPKNWMSANN7/events.json","paper":"https://pith.science/paper/SHC65RYF"},"agent_actions":{"view_html":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7","download_json":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7.json","view_paper":"https://pith.science/paper/SHC65RYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08435&json=true","fetch_graph":"https://pith.science/api/pith-number/SHC65RYFPTWIAPIGPKNWMSANN7/graph.json","fetch_events":"https://pith.science/api/pith-number/SHC65RYFPTWIAPIGPKNWMSANN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7/action/storage_attestation","attest_author":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7/action/author_attestation","sign_citation":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7/action/citation_signature","submit_replication":"https://pith.science/pith/SHC65RYFPTWIAPIGPKNWMSANN7/action/replication_record"}},"created_at":"2026-05-18T00:12:24.518146+00:00","updated_at":"2026-05-18T00:12:24.518146+00:00"}