{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QCEYYPJGXYYOKR5VWXTXX4HTCR","short_pith_number":"pith:QCEYYPJG","schema_version":"1.0","canonical_sha256":"80898c3d26be30e547b5b5e77bf0f3144849414c5635cc42af4c78f21fa2d7e1","source":{"kind":"arxiv","id":"1904.03976","version":3},"attestation_state":"computed","paper":{"title":"GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-spectrogram","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bajibabu Bollepalli, Junichi Yamagishi, Lauri Juvela, Paavo Alku","submitted_at":"2019-04-08T11:58:00Z","abstract_excerpt":"Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for modeling, but present additional challenges for vocoding (i.e., waveform generation from the acoustic features). High-quality synthesis can be achieved with neural vocoders, such as WaveNet, but such autoregressive models suffer from slow sequential inference. Meanwhile, their existing parallel inference counterparts are difficult to train and require increas"},"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":"1904.03976","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-04-08T11:58:00Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"b153a9c9777fe0438ca9e944257458066e61eeed6d7b74694929634fe3e0eef6","abstract_canon_sha256":"1d44244458a402e70f2f4f85d1b0887df79dfe42a89fb06c07f0edc453f1b4a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:13.542576Z","signature_b64":"vpnUboM8sEQD1Gx10OnyuJiT+iMdWXJMfGmOoyj6I8zskVrlu7SWpyOa5P8Svqh/TWiLbF2dT/LzWuy8o1VyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80898c3d26be30e547b5b5e77bf0f3144849414c5635cc42af4c78f21fa2d7e1","last_reissued_at":"2026-05-17T23:42:13.542080Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:13.542080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-spectrogram","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bajibabu Bollepalli, Junichi Yamagishi, Lauri Juvela, Paavo Alku","submitted_at":"2019-04-08T11:58:00Z","abstract_excerpt":"Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for modeling, but present additional challenges for vocoding (i.e., waveform generation from the acoustic features). High-quality synthesis can be achieved with neural vocoders, such as WaveNet, but such autoregressive models suffer from slow sequential inference. Meanwhile, their existing parallel inference counterparts are difficult to train and require increas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03976","kind":"arxiv","version":3},"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":"1904.03976","created_at":"2026-05-17T23:42:13.542148+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03976v3","created_at":"2026-05-17T23:42:13.542148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03976","created_at":"2026-05-17T23:42:13.542148+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCEYYPJGXYYO","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCEYYPJGXYYOKR5V","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCEYYPJG","created_at":"2026-05-18T12:33:27.125529+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/QCEYYPJGXYYOKR5VWXTXX4HTCR","json":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR.json","graph_json":"https://pith.science/api/pith-number/QCEYYPJGXYYOKR5VWXTXX4HTCR/graph.json","events_json":"https://pith.science/api/pith-number/QCEYYPJGXYYOKR5VWXTXX4HTCR/events.json","paper":"https://pith.science/paper/QCEYYPJG"},"agent_actions":{"view_html":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR","download_json":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR.json","view_paper":"https://pith.science/paper/QCEYYPJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03976&json=true","fetch_graph":"https://pith.science/api/pith-number/QCEYYPJGXYYOKR5VWXTXX4HTCR/graph.json","fetch_events":"https://pith.science/api/pith-number/QCEYYPJGXYYOKR5VWXTXX4HTCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR/action/storage_attestation","attest_author":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR/action/author_attestation","sign_citation":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR/action/citation_signature","submit_replication":"https://pith.science/pith/QCEYYPJGXYYOKR5VWXTXX4HTCR/action/replication_record"}},"created_at":"2026-05-17T23:42:13.542148+00:00","updated_at":"2026-05-17T23:42:13.542148+00:00"}