{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X3HLBY3DBNIJ27PORW6GADW6OD","short_pith_number":"pith:X3HLBY3D","schema_version":"1.0","canonical_sha256":"beceb0e3630b509d7dee8dbc600ede70f0da566b23f409bd9bd7fb93912f9255","source":{"kind":"arxiv","id":"1804.02549","version":1},"attestation_state":"computed","paper":{"title":"A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Jaime Lorenzo-Trueba, Junichi Yamagishi, Lauri Juvela, Shinji Takaki, Xin Wang","submitted_at":"2018-04-07T12:16:50Z","abstract_excerpt":"Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly compare new vocoding and acoustic modeling techniques with conventional approaches by means of a large scale crowdsourced evaluation. Results on acoustic models showed that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent net"},"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":"1804.02549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-04-07T12:16:50Z","cross_cats_sorted":["cs.CL","cs.SD","stat.ML"],"title_canon_sha256":"fe813589b5000cb72b563bba7b1963ae1c55c9e1c3dcccd6f766ffa90affd13e","abstract_canon_sha256":"77184a7004824ff43a92c3d698f20013d498f8e6ffcc33cebc2086675cabe30b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:59.157614Z","signature_b64":"tHSmh77fZSqte4Z5vF+8AHlCl6RYLvmjsrJzbTxPaBpxhLQRcARpI8VucGAkGJOOSzGRB/6auBW6Yd7NEZC4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beceb0e3630b509d7dee8dbc600ede70f0da566b23f409bd9bd7fb93912f9255","last_reissued_at":"2026-05-18T00:18:59.157181Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:59.157181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Jaime Lorenzo-Trueba, Junichi Yamagishi, Lauri Juvela, Shinji Takaki, Xin Wang","submitted_at":"2018-04-07T12:16:50Z","abstract_excerpt":"Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly compare new vocoding and acoustic modeling techniques with conventional approaches by means of a large scale crowdsourced evaluation. Results on acoustic models showed that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02549","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":"1804.02549","created_at":"2026-05-18T00:18:59.157243+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02549v1","created_at":"2026-05-18T00:18:59.157243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02549","created_at":"2026-05-18T00:18:59.157243+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3HLBY3DBNIJ","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3HLBY3DBNIJ27PO","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3HLBY3D","created_at":"2026-05-18T12:33:01.666342+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/X3HLBY3DBNIJ27PORW6GADW6OD","json":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD.json","graph_json":"https://pith.science/api/pith-number/X3HLBY3DBNIJ27PORW6GADW6OD/graph.json","events_json":"https://pith.science/api/pith-number/X3HLBY3DBNIJ27PORW6GADW6OD/events.json","paper":"https://pith.science/paper/X3HLBY3D"},"agent_actions":{"view_html":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD","download_json":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD.json","view_paper":"https://pith.science/paper/X3HLBY3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02549&json=true","fetch_graph":"https://pith.science/api/pith-number/X3HLBY3DBNIJ27PORW6GADW6OD/graph.json","fetch_events":"https://pith.science/api/pith-number/X3HLBY3DBNIJ27PORW6GADW6OD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD/action/storage_attestation","attest_author":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD/action/author_attestation","sign_citation":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD/action/citation_signature","submit_replication":"https://pith.science/pith/X3HLBY3DBNIJ27PORW6GADW6OD/action/replication_record"}},"created_at":"2026-05-18T00:18:59.157243+00:00","updated_at":"2026-05-18T00:18:59.157243+00:00"}