{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I2YWNCSUUYRONTJKHHHSF5VIPX","short_pith_number":"pith:I2YWNCSU","schema_version":"1.0","canonical_sha256":"46b1668a54a622e6cd2a39cf22f6a87dde2f9a2f555406d74f472d4e4d0981d4","source":{"kind":"arxiv","id":"2501.06146","version":2},"attestation_state":"computed","paper":{"title":"xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jan {\\O}stergaard, Jesper Jensen, Nikolai Lund K\\\"uhne, Zheng-Hua Tan","submitted_at":"2025-01-10T18:10:06Z","abstract_excerpt":"While attention-based architectures, such as Conformers, excel in speech enhancement, they face challenges such as scalability with respect to input sequence length. In contrast, the recently proposed Extended Long Short-Term Memory (xLSTM) architecture offers linear scalability. However, xLSTM-based models remain unexplored for speech enhancement. This paper introduces xLSTM-SENet, the first xLSTM-based single-channel speech enhancement system. A comparative analysis reveals that xLSTM-and notably, even LSTM-can match or outperform state-of-the-art Mamba- and Conformer-based systems across va"},"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":"2501.06146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-10T18:10:06Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"fa0db5e8cc6727ce09020f2797c76cfec721cb218ef9b30b9cc1a4c23884f170","abstract_canon_sha256":"f4e445f90ed2ce9427925484a3b9d10fe478314dcc946cfef41de8bc8a5e921e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:38.392589Z","signature_b64":"4HkM2QBiVJDVP3sdbTUcsSZdIe0WHiPGQOVWyXR6FofeW5N7wKxoydntEH+UCLy940BPTKeZHH1q9Cz58rlQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46b1668a54a622e6cd2a39cf22f6a87dde2f9a2f555406d74f472d4e4d0981d4","last_reissued_at":"2026-07-05T11:05:38.392115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:38.392115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jan {\\O}stergaard, Jesper Jensen, Nikolai Lund K\\\"uhne, Zheng-Hua Tan","submitted_at":"2025-01-10T18:10:06Z","abstract_excerpt":"While attention-based architectures, such as Conformers, excel in speech enhancement, they face challenges such as scalability with respect to input sequence length. In contrast, the recently proposed Extended Long Short-Term Memory (xLSTM) architecture offers linear scalability. However, xLSTM-based models remain unexplored for speech enhancement. This paper introduces xLSTM-SENet, the first xLSTM-based single-channel speech enhancement system. A comparative analysis reveals that xLSTM-and notably, even LSTM-can match or outperform state-of-the-art Mamba- and Conformer-based systems across va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06146","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/2501.06146/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":"2501.06146","created_at":"2026-07-05T11:05:38.392172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06146v2","created_at":"2026-07-05T11:05:38.392172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06146","created_at":"2026-07-05T11:05:38.392172+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2YWNCSUUYRO","created_at":"2026-07-05T11:05:38.392172+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2YWNCSUUYRONTJK","created_at":"2026-07-05T11:05:38.392172+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2YWNCSU","created_at":"2026-07-05T11:05:38.392172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19688","citing_title":"Latency-Configurable Streaming Speech Enhancement via Asymmetric Temporal Padding","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX","json":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX.json","graph_json":"https://pith.science/api/pith-number/I2YWNCSUUYRONTJKHHHSF5VIPX/graph.json","events_json":"https://pith.science/api/pith-number/I2YWNCSUUYRONTJKHHHSF5VIPX/events.json","paper":"https://pith.science/paper/I2YWNCSU"},"agent_actions":{"view_html":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX","download_json":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX.json","view_paper":"https://pith.science/paper/I2YWNCSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06146&json=true","fetch_graph":"https://pith.science/api/pith-number/I2YWNCSUUYRONTJKHHHSF5VIPX/graph.json","fetch_events":"https://pith.science/api/pith-number/I2YWNCSUUYRONTJKHHHSF5VIPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX/action/storage_attestation","attest_author":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX/action/author_attestation","sign_citation":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX/action/citation_signature","submit_replication":"https://pith.science/pith/I2YWNCSUUYRONTJKHHHSF5VIPX/action/replication_record"}},"created_at":"2026-07-05T11:05:38.392172+00:00","updated_at":"2026-07-05T11:05:38.392172+00:00"}