{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OR2KUB7I5ZAPY3R2ALHPLKR7MA","short_pith_number":"pith:OR2KUB7I","schema_version":"1.0","canonical_sha256":"7474aa07e8ee40fc6e3a02cef5aa3f6012ccd9c48437c6a92c1100e6b514e150","source":{"kind":"arxiv","id":"2605.25506","version":1},"attestation_state":"computed","paper":{"title":"WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hisashi Kawai, Sakriani Sakti, Takuma Okamoto, Wangzixi Zhou, Yamato Ohtani","submitted_at":"2026-05-25T07:09:58Z","abstract_excerpt":"Most neural vocoders are limited to one type: either GAN or diffusion-based. While state-of-the-art models like Vocos and WaveNeXt use powerful ConvNeXt-based generators, they have only been used in GAN frameworks and have limited performance in multi-speaker settings. Moreover, diffusion models, despite training faster than GANs, have slow CPU inference. In this paper, we introduce WaveNeXt 2, a unified ConvNeXt-based framework compatible with both GAN and diffusion vocoders. Its core innovation is residual denoising and sub-modeling, where each sub-model progressively refines the waveform. E"},"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":"2605.25506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-25T07:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"eda285a0e1b753ed3c3e1aef73727794c70fc175cf8ed78c762b76238cd38e12","abstract_canon_sha256":"5f50d88d7b8390c3efe1c8dec48da66b5c6eea1675dfe480960dcc97b3f2b149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:39.998467Z","signature_b64":"rcygVxQ/oh192Vma2ta7MPvDsGN2Q+ieYHfHsmxM1jiiHPVatGySquqDhsxn6uJxkFFF8nmz0vY1A100OvS5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7474aa07e8ee40fc6e3a02cef5aa3f6012ccd9c48437c6a92c1100e6b514e150","last_reissued_at":"2026-05-26T02:04:39.997621Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:39.997621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hisashi Kawai, Sakriani Sakti, Takuma Okamoto, Wangzixi Zhou, Yamato Ohtani","submitted_at":"2026-05-25T07:09:58Z","abstract_excerpt":"Most neural vocoders are limited to one type: either GAN or diffusion-based. While state-of-the-art models like Vocos and WaveNeXt use powerful ConvNeXt-based generators, they have only been used in GAN frameworks and have limited performance in multi-speaker settings. Moreover, diffusion models, despite training faster than GANs, have slow CPU inference. In this paper, we introduce WaveNeXt 2, a unified ConvNeXt-based framework compatible with both GAN and diffusion vocoders. Its core innovation is residual denoising and sub-modeling, where each sub-model progressively refines the waveform. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25506","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/2605.25506/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":"2605.25506","created_at":"2026-05-26T02:04:39.997775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25506v1","created_at":"2026-05-26T02:04:39.997775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25506","created_at":"2026-05-26T02:04:39.997775+00:00"},{"alias_kind":"pith_short_12","alias_value":"OR2KUB7I5ZAP","created_at":"2026-05-26T02:04:39.997775+00:00"},{"alias_kind":"pith_short_16","alias_value":"OR2KUB7I5ZAPY3R2","created_at":"2026-05-26T02:04:39.997775+00:00"},{"alias_kind":"pith_short_8","alias_value":"OR2KUB7I","created_at":"2026-05-26T02:04:39.997775+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/OR2KUB7I5ZAPY3R2ALHPLKR7MA","json":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA.json","graph_json":"https://pith.science/api/pith-number/OR2KUB7I5ZAPY3R2ALHPLKR7MA/graph.json","events_json":"https://pith.science/api/pith-number/OR2KUB7I5ZAPY3R2ALHPLKR7MA/events.json","paper":"https://pith.science/paper/OR2KUB7I"},"agent_actions":{"view_html":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA","download_json":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA.json","view_paper":"https://pith.science/paper/OR2KUB7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25506&json=true","fetch_graph":"https://pith.science/api/pith-number/OR2KUB7I5ZAPY3R2ALHPLKR7MA/graph.json","fetch_events":"https://pith.science/api/pith-number/OR2KUB7I5ZAPY3R2ALHPLKR7MA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA/action/storage_attestation","attest_author":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA/action/author_attestation","sign_citation":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA/action/citation_signature","submit_replication":"https://pith.science/pith/OR2KUB7I5ZAPY3R2ALHPLKR7MA/action/replication_record"}},"created_at":"2026-05-26T02:04:39.997775+00:00","updated_at":"2026-05-26T02:04:39.997775+00:00"}