{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MTTVIHC4UESKKC2ZT5WX3EKDZC","short_pith_number":"pith:MTTVIHC4","schema_version":"1.0","canonical_sha256":"64e7541c5ca124a50b599f6d7d9143c8bfac92229651aeb109295a5e9e37a04a","source":{"kind":"arxiv","id":"2312.01744","version":1},"attestation_state":"computed","paper":{"title":"SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bernd Edler, Martin Strauss, Nagashree K. S. Rao, Nicola Pia","submitted_at":"2023-12-04T09:10:08Z","abstract_excerpt":"This paper proposes SEFGAN, a Deep Neural Network (DNN) combining maximum likelihood training and Generative Adversarial Networks (GANs) for efficient speech enhancement (SE). For this, a DNN is trained to synthesize the enhanced speech conditioned on noisy speech using a Normalizing Flow (NF) as generator in a GAN framework. While the combination of likelihood models and GANs is not trivial, SEFGAN demonstrates that a hybrid adversarial and maximum likelihood training approach enables the model to maintain high quality audio generation and log-likelihood estimation. Our experiments indicate t"},"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":"2312.01744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-12-04T09:10:08Z","cross_cats_sorted":[],"title_canon_sha256":"61c7b3743b0376535d61964e8de657ba94672a4a7b00d4d39f501846e0113999","abstract_canon_sha256":"686b137f9e54db821109b08f482392208341809501ca4898cd9f2f5210fbd278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:59.040417Z","signature_b64":"bGYkURg1A/l/DhK7QBnabRyHY1v4LjHCCaHAQ43XcG2BtliiX7JoerDXsWuZ8x7NvhGpsd+0xVlk7VkUqfQMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64e7541c5ca124a50b599f6d7d9143c8bfac92229651aeb109295a5e9e37a04a","last_reissued_at":"2026-07-05T07:19:59.039960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:59.039960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bernd Edler, Martin Strauss, Nagashree K. S. Rao, Nicola Pia","submitted_at":"2023-12-04T09:10:08Z","abstract_excerpt":"This paper proposes SEFGAN, a Deep Neural Network (DNN) combining maximum likelihood training and Generative Adversarial Networks (GANs) for efficient speech enhancement (SE). For this, a DNN is trained to synthesize the enhanced speech conditioned on noisy speech using a Normalizing Flow (NF) as generator in a GAN framework. While the combination of likelihood models and GANs is not trivial, SEFGAN demonstrates that a hybrid adversarial and maximum likelihood training approach enables the model to maintain high quality audio generation and log-likelihood estimation. Our experiments indicate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01744","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/2312.01744/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":"2312.01744","created_at":"2026-07-05T07:19:59.040029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01744v1","created_at":"2026-07-05T07:19:59.040029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01744","created_at":"2026-07-05T07:19:59.040029+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTTVIHC4UESK","created_at":"2026-07-05T07:19:59.040029+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTTVIHC4UESKKC2Z","created_at":"2026-07-05T07:19:59.040029+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTTVIHC4","created_at":"2026-07-05T07:19:59.040029+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/MTTVIHC4UESKKC2ZT5WX3EKDZC","json":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC.json","graph_json":"https://pith.science/api/pith-number/MTTVIHC4UESKKC2ZT5WX3EKDZC/graph.json","events_json":"https://pith.science/api/pith-number/MTTVIHC4UESKKC2ZT5WX3EKDZC/events.json","paper":"https://pith.science/paper/MTTVIHC4"},"agent_actions":{"view_html":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC","download_json":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC.json","view_paper":"https://pith.science/paper/MTTVIHC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01744&json=true","fetch_graph":"https://pith.science/api/pith-number/MTTVIHC4UESKKC2ZT5WX3EKDZC/graph.json","fetch_events":"https://pith.science/api/pith-number/MTTVIHC4UESKKC2ZT5WX3EKDZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC/action/storage_attestation","attest_author":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC/action/author_attestation","sign_citation":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC/action/citation_signature","submit_replication":"https://pith.science/pith/MTTVIHC4UESKKC2ZT5WX3EKDZC/action/replication_record"}},"created_at":"2026-07-05T07:19:59.040029+00:00","updated_at":"2026-07-05T07:19:59.040029+00:00"}