{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6DUOXCW7WGMIIO65SB6VORENG2","short_pith_number":"pith:6DUOXCW7","schema_version":"1.0","canonical_sha256":"f0e8eb8adfb198843bdd907d57448d369a5743dd570e951be3f50aecb70791b2","source":{"kind":"arxiv","id":"2305.08541","version":1},"attestation_state":"computed","paper":{"title":"Ripple sparse self-attention for monaural speech enhancement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Hongxu Zhu, Qiquan Zhang, Qi Song, Xinyuan Qian, Zhaoheng Ni","submitted_at":"2023-05-15T11:12:20Z","abstract_excerpt":"The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows each time frame to attend to all time frames, neglecting the strong local correlations of speech signals. This study presents a simple yet effective sparse self-attention for speech enhancement, called ripple attention, which simultaneously performs fine- and coarse-grained modeling for local and global dependencies, respectively. Specifically, we employ loc"},"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":"2305.08541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-15T11:12:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"418202a7b3a3700cb9508bfba25bd8a4e4ef57df623937c856e368c718a5002d","abstract_canon_sha256":"4ba0d826a1621c5fa3988c74c9b8ce06862747294c5ad8408766a8259e4d56d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:03.099368Z","signature_b64":"EodF64Vr5M6IegLq6BAE5k6VdRtzjrNkpLfeR636ljYukxN6cdaf0KW38W8JRIzl43hdO7Mvs1x7t4fqJj+aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0e8eb8adfb198843bdd907d57448d369a5743dd570e951be3f50aecb70791b2","last_reissued_at":"2026-07-05T06:10:03.098868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:03.098868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ripple sparse self-attention for monaural speech enhancement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Hongxu Zhu, Qiquan Zhang, Qi Song, Xinyuan Qian, Zhaoheng Ni","submitted_at":"2023-05-15T11:12:20Z","abstract_excerpt":"The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows each time frame to attend to all time frames, neglecting the strong local correlations of speech signals. This study presents a simple yet effective sparse self-attention for speech enhancement, called ripple attention, which simultaneously performs fine- and coarse-grained modeling for local and global dependencies, respectively. Specifically, we employ loc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08541","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/2305.08541/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":"2305.08541","created_at":"2026-07-05T06:10:03.098927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08541v1","created_at":"2026-07-05T06:10:03.098927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08541","created_at":"2026-07-05T06:10:03.098927+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DUOXCW7WGMI","created_at":"2026-07-05T06:10:03.098927+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DUOXCW7WGMIIO65","created_at":"2026-07-05T06:10:03.098927+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DUOXCW7","created_at":"2026-07-05T06:10:03.098927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10046","citing_title":"Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2","json":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2.json","graph_json":"https://pith.science/api/pith-number/6DUOXCW7WGMIIO65SB6VORENG2/graph.json","events_json":"https://pith.science/api/pith-number/6DUOXCW7WGMIIO65SB6VORENG2/events.json","paper":"https://pith.science/paper/6DUOXCW7"},"agent_actions":{"view_html":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2","download_json":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2.json","view_paper":"https://pith.science/paper/6DUOXCW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08541&json=true","fetch_graph":"https://pith.science/api/pith-number/6DUOXCW7WGMIIO65SB6VORENG2/graph.json","fetch_events":"https://pith.science/api/pith-number/6DUOXCW7WGMIIO65SB6VORENG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2/action/storage_attestation","attest_author":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2/action/author_attestation","sign_citation":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2/action/citation_signature","submit_replication":"https://pith.science/pith/6DUOXCW7WGMIIO65SB6VORENG2/action/replication_record"}},"created_at":"2026-07-05T06:10:03.098927+00:00","updated_at":"2026-07-05T06:10:03.098927+00:00"}