{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C3B7YF7EMX5BCFCGYLDMZA62K7","short_pith_number":"pith:C3B7YF7E","schema_version":"1.0","canonical_sha256":"16c3fc17e465fa111446c2c6cc83da57e3b66d9106019e53064817df94575791","source":{"kind":"arxiv","id":"2303.13909","version":1},"attestation_state":"computed","paper":{"title":"Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Hirokazu Kameoka, Kou Tanaka, Shogo Seki, Takuhiro Kaneko","submitted_at":"2023-03-24T10:46:40Z","abstract_excerpt":"In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quality. An ensemble of discriminators is commonly used in recent neural vocoders (e.g., HiFi-GAN) and end-to-end text-to-speech (TTS) systems (e.g., VITS) to scrutinize waveforms from multiple perspectives. Such discriminators allow synthesized speech to adequately approach real speech; however, they require an increase in the model size and computation time according to the increase in the number of discriminators. Alte"},"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":"2303.13909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-24T10:46:40Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"d216c87fbeae796db8bea5bb0830ac7865fc608a2e463622442087f344a6ba5d","abstract_canon_sha256":"e81c837bd67a0b7509438562f6dc768e0619cc4fffb841c9864c6cd8e582e094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:21.468123Z","signature_b64":"7CUmUAYf/0jGiJLEB/JbrMy4zDb5DZN53vlcMKvHi34aV+6iT2SuyLuYiJk5y/6IDNEwZRNJrZLZX1amFt0EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16c3fc17e465fa111446c2c6cc83da57e3b66d9106019e53064817df94575791","last_reissued_at":"2026-07-05T05:54:21.467667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:21.467667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Hirokazu Kameoka, Kou Tanaka, Shogo Seki, Takuhiro Kaneko","submitted_at":"2023-03-24T10:46:40Z","abstract_excerpt":"In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quality. An ensemble of discriminators is commonly used in recent neural vocoders (e.g., HiFi-GAN) and end-to-end text-to-speech (TTS) systems (e.g., VITS) to scrutinize waveforms from multiple perspectives. Such discriminators allow synthesized speech to adequately approach real speech; however, they require an increase in the model size and computation time according to the increase in the number of discriminators. Alte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13909","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.13909/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2303.13909","created_at":"2026-07-05T05:54:21.467735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13909v1","created_at":"2026-07-05T05:54:21.467735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13909","created_at":"2026-07-05T05:54:21.467735+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3B7YF7EMX5B","created_at":"2026-07-05T05:54:21.467735+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3B7YF7EMX5BCFCG","created_at":"2026-07-05T05:54:21.467735+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3B7YF7E","created_at":"2026-07-05T05:54:21.467735+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/C3B7YF7EMX5BCFCGYLDMZA62K7","json":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7.json","graph_json":"https://pith.science/api/pith-number/C3B7YF7EMX5BCFCGYLDMZA62K7/graph.json","events_json":"https://pith.science/api/pith-number/C3B7YF7EMX5BCFCGYLDMZA62K7/events.json","paper":"https://pith.science/paper/C3B7YF7E"},"agent_actions":{"view_html":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7","download_json":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7.json","view_paper":"https://pith.science/paper/C3B7YF7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13909&json=true","fetch_graph":"https://pith.science/api/pith-number/C3B7YF7EMX5BCFCGYLDMZA62K7/graph.json","fetch_events":"https://pith.science/api/pith-number/C3B7YF7EMX5BCFCGYLDMZA62K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7/action/storage_attestation","attest_author":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7/action/author_attestation","sign_citation":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7/action/citation_signature","submit_replication":"https://pith.science/pith/C3B7YF7EMX5BCFCGYLDMZA62K7/action/replication_record"}},"created_at":"2026-07-05T05:54:21.467735+00:00","updated_at":"2026-07-05T05:54:21.467735+00:00"}