{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NFLPV63HC7A25XR2T4EXAG56KY","short_pith_number":"pith:NFLPV63H","schema_version":"1.0","canonical_sha256":"6956fafb6717c1aede3a9f09701bbe5612fbf2945c4da3a31956d6226d15078f","source":{"kind":"arxiv","id":"1904.07944","version":2},"attestation_state":"computed","paper":{"title":"Expediting TTS Synthesis with Adversarial Vocoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Julian McAuley, Miller Puckette, Paarth Neekhara, Shlomo Dubnov","submitted_at":"2019-04-16T19:42:43Z","abstract_excerpt":"Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck in modern TTS pipelines. We propose an alternative approach which utilizes generative adversarial networks (GANs) to learn mappings from perceptually-informed spectrograms to simple magnitude spectrograms which can be heuristically vocoded. Through a user study, we show that our approach significantly outperforms na\\\"ive vocoding strategies while being hundr"},"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":"1904.07944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-16T19:42:43Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"64c112705c6eb02ea384b8c977c15308f80791e848d3f4554ae07386a86f81f6","abstract_canon_sha256":"0c94369a6655a1f00e5a5a4e1f0890c2274d86baad89b59bffae340590d619e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:30.252543Z","signature_b64":"RD9FqLVWBnC+Z8Z2uco35t3G0WnMDhnkZCeXjcaRWkmWil4xpNapw7j8zVQ6do/3BDvT4Uwnc/fQtBOoU5gMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6956fafb6717c1aede3a9f09701bbe5612fbf2945c4da3a31956d6226d15078f","last_reissued_at":"2026-05-17T23:39:30.252065Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:30.252065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expediting TTS Synthesis with Adversarial Vocoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Julian McAuley, Miller Puckette, Paarth Neekhara, Shlomo Dubnov","submitted_at":"2019-04-16T19:42:43Z","abstract_excerpt":"Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck in modern TTS pipelines. We propose an alternative approach which utilizes generative adversarial networks (GANs) to learn mappings from perceptually-informed spectrograms to simple magnitude spectrograms which can be heuristically vocoded. Through a user study, we show that our approach significantly outperforms na\\\"ive vocoding strategies while being hundr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07944","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":"1904.07944","created_at":"2026-05-17T23:39:30.252140+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07944v2","created_at":"2026-05-17T23:39:30.252140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07944","created_at":"2026-05-17T23:39:30.252140+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFLPV63HC7A2","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFLPV63HC7A25XR2","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFLPV63H","created_at":"2026-05-18T12:33:24.271573+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/NFLPV63HC7A25XR2T4EXAG56KY","json":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY.json","graph_json":"https://pith.science/api/pith-number/NFLPV63HC7A25XR2T4EXAG56KY/graph.json","events_json":"https://pith.science/api/pith-number/NFLPV63HC7A25XR2T4EXAG56KY/events.json","paper":"https://pith.science/paper/NFLPV63H"},"agent_actions":{"view_html":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY","download_json":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY.json","view_paper":"https://pith.science/paper/NFLPV63H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07944&json=true","fetch_graph":"https://pith.science/api/pith-number/NFLPV63HC7A25XR2T4EXAG56KY/graph.json","fetch_events":"https://pith.science/api/pith-number/NFLPV63HC7A25XR2T4EXAG56KY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY/action/storage_attestation","attest_author":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY/action/author_attestation","sign_citation":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY/action/citation_signature","submit_replication":"https://pith.science/pith/NFLPV63HC7A25XR2T4EXAG56KY/action/replication_record"}},"created_at":"2026-05-17T23:39:30.252140+00:00","updated_at":"2026-05-17T23:39:30.252140+00:00"}