{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KT3GMEDBRN37ODFPSQA4PAG2RY","short_pith_number":"pith:KT3GMEDB","schema_version":"1.0","canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","source":{"kind":"arxiv","id":"2412.08577","version":1},"attestation_state":"computed","paper":{"title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Chunyu Qiang, Hongming Guo, Ruibo Fu, Shuai Liu, Shuchen Shi, Tao Wang, Xuefei Liu, Ya Li, Yizhong Geng, Yukun Liu, Zhengqi Wen","submitted_at":"2024-12-11T17:51:44Z","abstract_excerpt":"Text-to-audio (TTA) model is capable of generating diverse audio from textual prompts. However, most mainstream TTA models, which predominantly rely on Mel-spectrograms, still face challenges in producing audio with rich content. The intricate details and texture required in Mel-spectrograms for such audio often surpass the models' capacity, leading to outputs that are blurred or lack coherence. In this paper, we begin by investigating the critical role of U-Net in Mel-spectrogram generation. Our analysis shows that in U-Net structure, high-frequency components in skip-connections and the back"},"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":"2412.08577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:51:44Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"2a5465a6ed7d9d4ba9b2dd6592a39a4f90b23390d16f63a95fb7c9e0f2d78c5e","abstract_canon_sha256":"43ca7c7400e1ffd39e5c5dd7f0b234f74459eea68e8365110e5e841e935c92d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:52.134230Z","signature_b64":"KiDNPuD3v0OU02OCS5EvXQ5vMnIponQjVqP2SjRHhGezBuByHxnk9y51z+1Bn/UYGCb+nfk0K9WIG9hf67BbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54f66610618b77f70caf9401c780da8e198202786b10ec68e0cd6fa6a404567d","last_reissued_at":"2026-07-05T09:47:52.133773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:52.133773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Chunyu Qiang, Hongming Guo, Ruibo Fu, Shuai Liu, Shuchen Shi, Tao Wang, Xuefei Liu, Ya Li, Yizhong Geng, Yukun Liu, Zhengqi Wen","submitted_at":"2024-12-11T17:51:44Z","abstract_excerpt":"Text-to-audio (TTA) model is capable of generating diverse audio from textual prompts. However, most mainstream TTA models, which predominantly rely on Mel-spectrograms, still face challenges in producing audio with rich content. The intricate details and texture required in Mel-spectrograms for such audio often surpass the models' capacity, leading to outputs that are blurred or lack coherence. In this paper, we begin by investigating the critical role of U-Net in Mel-spectrogram generation. Our analysis shows that in U-Net structure, high-frequency components in skip-connections and the back"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08577","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/2412.08577/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":"2412.08577","created_at":"2026-07-05T09:47:52.133831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08577v1","created_at":"2026-07-05T09:47:52.133831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08577","created_at":"2026-07-05T09:47:52.133831+00:00"},{"alias_kind":"pith_short_12","alias_value":"KT3GMEDBRN37","created_at":"2026-07-05T09:47:52.133831+00:00"},{"alias_kind":"pith_short_16","alias_value":"KT3GMEDBRN37ODFP","created_at":"2026-07-05T09:47:52.133831+00:00"},{"alias_kind":"pith_short_8","alias_value":"KT3GMEDB","created_at":"2026-07-05T09:47:52.133831+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/KT3GMEDBRN37ODFPSQA4PAG2RY","json":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY.json","graph_json":"https://pith.science/api/pith-number/KT3GMEDBRN37ODFPSQA4PAG2RY/graph.json","events_json":"https://pith.science/api/pith-number/KT3GMEDBRN37ODFPSQA4PAG2RY/events.json","paper":"https://pith.science/paper/KT3GMEDB"},"agent_actions":{"view_html":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY","download_json":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY.json","view_paper":"https://pith.science/paper/KT3GMEDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08577&json=true","fetch_graph":"https://pith.science/api/pith-number/KT3GMEDBRN37ODFPSQA4PAG2RY/graph.json","fetch_events":"https://pith.science/api/pith-number/KT3GMEDBRN37ODFPSQA4PAG2RY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/action/storage_attestation","attest_author":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/action/author_attestation","sign_citation":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/action/citation_signature","submit_replication":"https://pith.science/pith/KT3GMEDBRN37ODFPSQA4PAG2RY/action/replication_record"}},"created_at":"2026-07-05T09:47:52.133831+00:00","updated_at":"2026-07-05T09:47:52.133831+00:00"}