{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GFCNL2MZL5GH7AR3TLJT4RITLZ","short_pith_number":"pith:GFCNL2MZ","schema_version":"1.0","canonical_sha256":"3144d5e9995f4c7f823b9ad33e45135e606c8fc7f905ce01f73bf6535671f4a7","source":{"kind":"arxiv","id":"1810.11946","version":4},"attestation_state":"computed","paper":{"title":"Neural source-filter-based waveform model for statistical parametric speech synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Junichi Yamagishi, Shinji Takaki, Xin Wang","submitted_at":"2018-10-29T04:10:40Z","abstract_excerpt":"Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were recently reported, they may be prohibitively complicated due to the use of a distilling training method and the blend of other disparate training criteria. This study proposes a non-AR neural source-filter waveform model that can be directly trained using spectrum-based training criteria and the stochastic gradient descent method. Given the input acoustic features"},"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":"1810.11946","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2018-10-29T04:10:40Z","cross_cats_sorted":["cs.SD","stat.ML"],"title_canon_sha256":"1d4e0a497043b9443fd994ca90a569674a3701e7d5e48b1b622e3fe6ddb1b086","abstract_canon_sha256":"08a1e0ffafcc1a21b5f22fd1413cbd899169d9ebb5b7cf5e6acd61d7950072ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:39.723977Z","signature_b64":"SrfjFm6TwwaQCUbcnqtuUGf3rg+ts5KMpwa2m3F9+DDscTtDmTxyHsnDjQcpSoOkVDYVxfcFNidFSu6tPFe2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3144d5e9995f4c7f823b9ad33e45135e606c8fc7f905ce01f73bf6535671f4a7","last_reissued_at":"2026-05-17T23:47:39.723522Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:39.723522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural source-filter-based waveform model for statistical parametric speech synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Junichi Yamagishi, Shinji Takaki, Xin Wang","submitted_at":"2018-10-29T04:10:40Z","abstract_excerpt":"Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were recently reported, they may be prohibitively complicated due to the use of a distilling training method and the blend of other disparate training criteria. This study proposes a non-AR neural source-filter waveform model that can be directly trained using spectrum-based training criteria and the stochastic gradient descent method. Given the input acoustic features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11946","kind":"arxiv","version":4},"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":"1810.11946","created_at":"2026-05-17T23:47:39.723598+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11946v4","created_at":"2026-05-17T23:47:39.723598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11946","created_at":"2026-05-17T23:47:39.723598+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFCNL2MZL5GH","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFCNL2MZL5GH7AR3","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFCNL2MZ","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ","json":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ.json","graph_json":"https://pith.science/api/pith-number/GFCNL2MZL5GH7AR3TLJT4RITLZ/graph.json","events_json":"https://pith.science/api/pith-number/GFCNL2MZL5GH7AR3TLJT4RITLZ/events.json","paper":"https://pith.science/paper/GFCNL2MZ"},"agent_actions":{"view_html":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ","download_json":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ.json","view_paper":"https://pith.science/paper/GFCNL2MZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11946&json=true","fetch_graph":"https://pith.science/api/pith-number/GFCNL2MZL5GH7AR3TLJT4RITLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GFCNL2MZL5GH7AR3TLJT4RITLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ/action/storage_attestation","attest_author":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ/action/author_attestation","sign_citation":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ/action/citation_signature","submit_replication":"https://pith.science/pith/GFCNL2MZL5GH7AR3TLJT4RITLZ/action/replication_record"}},"created_at":"2026-05-17T23:47:39.723598+00:00","updated_at":"2026-05-17T23:47:39.723598+00:00"}