{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ECSPTYJFHRQ4GHZE4YIHWENYHZ","short_pith_number":"pith:ECSPTYJF","schema_version":"1.0","canonical_sha256":"20a4f9e1253c61c31f24e6107b11b83e48d046ae70b2486581d58658437b2daa","source":{"kind":"arxiv","id":"2508.07711","version":1},"attestation_state":"computed","paper":{"title":"Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hui-Peng Du, Rui-Chen Zheng, Yang Ai, Ye-Xin Lu, Zhen-Hua Ling","submitted_at":"2025-08-11T07:38:48Z","abstract_excerpt":"Recently, mainstream mel-spectrogram-based neural vocoders rely on generative adversarial network (GAN) for high-fidelity speech generation, e.g., HiFi-GAN and BigVGAN. However, the use of GAN restricts training efficiency and model complexity. Therefore, this paper proposes a novel FreeGAN vocoder, aiming to answer the question of whether GAN is necessary for mel-spectrogram-based neural vocoders. The FreeGAN employs an amplitude-phase serial prediction framework, eliminating the need for GAN training. It incorporates amplitude prior input, SNAKE-ConvNeXt v2 backbone and frequency-weighted an"},"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":"2508.07711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-11T07:38:48Z","cross_cats_sorted":[],"title_canon_sha256":"822d28b46dc9ffa4b0dedc5778bd10bf7e75f774cc2b185fcb8351cadd42dc76","abstract_canon_sha256":"68859ee10434dbc4bfbd30d4f0cb100c43689fc405a9864819339fd0287eb638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:50.967510Z","signature_b64":"CbWr3BJaCKBFOjWpNmpLxQeT+U90j6Y7WGRek54nHIQsr/cI4qY6K3nPDHQI9QHrpeMNez1JUUjcqqxo6ReMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20a4f9e1253c61c31f24e6107b11b83e48d046ae70b2486581d58658437b2daa","last_reissued_at":"2026-07-05T11:51:50.967148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:50.967148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hui-Peng Du, Rui-Chen Zheng, Yang Ai, Ye-Xin Lu, Zhen-Hua Ling","submitted_at":"2025-08-11T07:38:48Z","abstract_excerpt":"Recently, mainstream mel-spectrogram-based neural vocoders rely on generative adversarial network (GAN) for high-fidelity speech generation, e.g., HiFi-GAN and BigVGAN. However, the use of GAN restricts training efficiency and model complexity. Therefore, this paper proposes a novel FreeGAN vocoder, aiming to answer the question of whether GAN is necessary for mel-spectrogram-based neural vocoders. The FreeGAN employs an amplitude-phase serial prediction framework, eliminating the need for GAN training. It incorporates amplitude prior input, SNAKE-ConvNeXt v2 backbone and frequency-weighted an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07711","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/2508.07711/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":"2508.07711","created_at":"2026-07-05T11:51:50.967202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07711v1","created_at":"2026-07-05T11:51:50.967202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07711","created_at":"2026-07-05T11:51:50.967202+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECSPTYJFHRQ4","created_at":"2026-07-05T11:51:50.967202+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECSPTYJFHRQ4GHZE","created_at":"2026-07-05T11:51:50.967202+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECSPTYJF","created_at":"2026-07-05T11:51:50.967202+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/ECSPTYJFHRQ4GHZE4YIHWENYHZ","json":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ.json","graph_json":"https://pith.science/api/pith-number/ECSPTYJFHRQ4GHZE4YIHWENYHZ/graph.json","events_json":"https://pith.science/api/pith-number/ECSPTYJFHRQ4GHZE4YIHWENYHZ/events.json","paper":"https://pith.science/paper/ECSPTYJF"},"agent_actions":{"view_html":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ","download_json":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ.json","view_paper":"https://pith.science/paper/ECSPTYJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07711&json=true","fetch_graph":"https://pith.science/api/pith-number/ECSPTYJFHRQ4GHZE4YIHWENYHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ECSPTYJFHRQ4GHZE4YIHWENYHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ/action/storage_attestation","attest_author":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ/action/author_attestation","sign_citation":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ/action/citation_signature","submit_replication":"https://pith.science/pith/ECSPTYJFHRQ4GHZE4YIHWENYHZ/action/replication_record"}},"created_at":"2026-07-05T11:51:50.967202+00:00","updated_at":"2026-07-05T11:51:50.967202+00:00"}