{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U6O64MZCJ3CXLJBKCLDGPCHYE2","short_pith_number":"pith:U6O64MZC","schema_version":"1.0","canonical_sha256":"a79dee33224ec575a42a12c66788f826a5431aec425a5302322e48cbf24744f1","source":{"kind":"arxiv","id":"1806.08619","version":1},"attestation_state":"computed","paper":{"title":"Multi-task WaveNet: A Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Yongguo Kang, Yu Gu","submitted_at":"2018-06-22T12:12:54Z","abstract_excerpt":"This paper introduces an improved generative model for statistical parametric speech synthesis (SPSS) based on WaveNet under a multi-task learning framework. Different from the original WaveNet model, the proposed Multi-task WaveNet employs the frame-level acoustic feature prediction as the secondary task and the external fundamental frequency prediction model for the original WaveNet can be removed. Therefore the improved WaveNet can generate high-quality speech waveforms only conditioned on linguistic features. Multi-task WaveNet can produce more natural and expressive speech by addressing 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":"1806.08619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-06-22T12:12:54Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"8cc34291c93f887f6966b08c5c4474a3fb7589f6ed2fe11d97b8614f5c2bc109","abstract_canon_sha256":"b2c204c73de63837d5f770d8defc3b23d71c1c5a7a60c06abb184f00c8613195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:36.646881Z","signature_b64":"bQzCnvTUkPzbFJnH6uZvCscnO/B2vVldYepsZ2+rIaCzlPSglYnZLsLCNukdQ0eQCSB6zu5btcFtS/GSn0QAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a79dee33224ec575a42a12c66788f826a5431aec425a5302322e48cbf24744f1","last_reissued_at":"2026-05-18T00:12:36.646123Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:36.646123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task WaveNet: A Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Yongguo Kang, Yu Gu","submitted_at":"2018-06-22T12:12:54Z","abstract_excerpt":"This paper introduces an improved generative model for statistical parametric speech synthesis (SPSS) based on WaveNet under a multi-task learning framework. Different from the original WaveNet model, the proposed Multi-task WaveNet employs the frame-level acoustic feature prediction as the secondary task and the external fundamental frequency prediction model for the original WaveNet can be removed. Therefore the improved WaveNet can generate high-quality speech waveforms only conditioned on linguistic features. Multi-task WaveNet can produce more natural and expressive speech by addressing t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08619","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":"1806.08619","created_at":"2026-05-18T00:12:36.646248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.08619v1","created_at":"2026-05-18T00:12:36.646248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08619","created_at":"2026-05-18T00:12:36.646248+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6O64MZCJ3CX","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6O64MZCJ3CXLJBK","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6O64MZC","created_at":"2026-05-18T12:32:56.356000+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/U6O64MZCJ3CXLJBKCLDGPCHYE2","json":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2.json","graph_json":"https://pith.science/api/pith-number/U6O64MZCJ3CXLJBKCLDGPCHYE2/graph.json","events_json":"https://pith.science/api/pith-number/U6O64MZCJ3CXLJBKCLDGPCHYE2/events.json","paper":"https://pith.science/paper/U6O64MZC"},"agent_actions":{"view_html":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2","download_json":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2.json","view_paper":"https://pith.science/paper/U6O64MZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.08619&json=true","fetch_graph":"https://pith.science/api/pith-number/U6O64MZCJ3CXLJBKCLDGPCHYE2/graph.json","fetch_events":"https://pith.science/api/pith-number/U6O64MZCJ3CXLJBKCLDGPCHYE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2/action/storage_attestation","attest_author":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2/action/author_attestation","sign_citation":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2/action/citation_signature","submit_replication":"https://pith.science/pith/U6O64MZCJ3CXLJBKCLDGPCHYE2/action/replication_record"}},"created_at":"2026-05-18T00:12:36.646248+00:00","updated_at":"2026-05-18T00:12:36.646248+00:00"}