{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:62TUT3QEZ5KHUAEF6BJORJGVFE","short_pith_number":"pith:62TUT3QE","schema_version":"1.0","canonical_sha256":"f6a749ee04cf547a0085f052e8a4d5292d8496b52f4cb37f9e324f1e528f4873","source":{"kind":"arxiv","id":"2311.08667","version":2},"attestation_state":"computed","paper":{"title":"EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ge Zhu, Marc-Andr\\'e Carbonneau, Yutong Wen, Zhiyao Duan","submitted_at":"2023-11-15T03:27:35Z","abstract_excerpt":"Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In this paper, we propose EDMSound, a diffusion-based generative model in spectrogram domain under the framework of elucidated diffusion models (EDM). Combining with efficient deterministic sampler, we achieved similar Fr\\'echet audio distance (FAD) score as top-ranked baseline with only 10 steps and reached state-of-the-art performance with 50 steps on the DCAS"},"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":"2311.08667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-15T03:27:35Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2b4c75b34fc2fd907441dd0d0f5331d6c179dbfac65e47f87622533c47559326","abstract_canon_sha256":"99270dbe5b28e9c71cab6a04ab4ecec820540b30142ca427789e7e02bfbb189f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:21.329983Z","signature_b64":"QlWyZcVh+JzfPZs+HAx5MW7OoASfKnorTL7lyJ1JCmEdbAhwnR3dc4efx9fNkQynUFSw1iZQoyeqp8ShFXFpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6a749ee04cf547a0085f052e8a4d5292d8496b52f4cb37f9e324f1e528f4873","last_reissued_at":"2026-07-05T07:14:21.329483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:21.329483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ge Zhu, Marc-Andr\\'e Carbonneau, Yutong Wen, Zhiyao Duan","submitted_at":"2023-11-15T03:27:35Z","abstract_excerpt":"Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In this paper, we propose EDMSound, a diffusion-based generative model in spectrogram domain under the framework of elucidated diffusion models (EDM). Combining with efficient deterministic sampler, we achieved similar Fr\\'echet audio distance (FAD) score as top-ranked baseline with only 10 steps and reached state-of-the-art performance with 50 steps on the DCAS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08667","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.08667/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":"2311.08667","created_at":"2026-07-05T07:14:21.329538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08667v2","created_at":"2026-07-05T07:14:21.329538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08667","created_at":"2026-07-05T07:14:21.329538+00:00"},{"alias_kind":"pith_short_12","alias_value":"62TUT3QEZ5KH","created_at":"2026-07-05T07:14:21.329538+00:00"},{"alias_kind":"pith_short_16","alias_value":"62TUT3QEZ5KHUAEF","created_at":"2026-07-05T07:14:21.329538+00:00"},{"alias_kind":"pith_short_8","alias_value":"62TUT3QE","created_at":"2026-07-05T07:14:21.329538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.26007","citing_title":"MARS: Sound Generation via Multi-Channel Autoregression on Spectrograms","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13910","citing_title":"Covariance-aware sampling for Diffusion Models","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE","json":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE.json","graph_json":"https://pith.science/api/pith-number/62TUT3QEZ5KHUAEF6BJORJGVFE/graph.json","events_json":"https://pith.science/api/pith-number/62TUT3QEZ5KHUAEF6BJORJGVFE/events.json","paper":"https://pith.science/paper/62TUT3QE"},"agent_actions":{"view_html":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE","download_json":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE.json","view_paper":"https://pith.science/paper/62TUT3QE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08667&json=true","fetch_graph":"https://pith.science/api/pith-number/62TUT3QEZ5KHUAEF6BJORJGVFE/graph.json","fetch_events":"https://pith.science/api/pith-number/62TUT3QEZ5KHUAEF6BJORJGVFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE/action/storage_attestation","attest_author":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE/action/author_attestation","sign_citation":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE/action/citation_signature","submit_replication":"https://pith.science/pith/62TUT3QEZ5KHUAEF6BJORJGVFE/action/replication_record"}},"created_at":"2026-07-05T07:14:21.329538+00:00","updated_at":"2026-07-05T07:14:21.329538+00:00"}