{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UGYDH5FQKD4BOESF5XWP3FSQ7Z","short_pith_number":"pith:UGYDH5FQ","schema_version":"1.0","canonical_sha256":"a1b033f4b050f8171245edecfd9650fe72342914ba8e7fba7a43caa0e909290b","source":{"kind":"arxiv","id":"2405.16797","version":1},"attestation_state":"computed","paper":{"title":"A Real-Time Voice Activity Detection Based On Lightweight Neural","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Di Wang, Jidong Jia, Pei Zhao","submitted_at":"2024-05-27T03:31:16Z","abstract_excerpt":"Voice activity detection (VAD) is the task of detecting speech in an audio stream, which is challenging due to numerous unseen noises and low signal-to-noise ratios in real environments. Recently, neural network-based VADs have alleviated the degradation of performance to some extent. However, the majority of existing studies have employed excessively large models and incorporated future context, while neglecting to evaluate the operational efficiency and latency of the models. In this paper, we propose a lightweight and real-time neural network called MagicNet, which utilizes casual and depth"},"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":"2405.16797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-05-27T03:31:16Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"613a07b1411e6d23ffe6848083bb6495a7a780122a4801615fde8aee77675567","abstract_canon_sha256":"c06cb605a792ac0bf6a0d59901ef2716650902811f7b8ae0c20eb9038cbefaa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:35.593065Z","signature_b64":"n3GGcPC7Ol7HyWOaSiRYA1BCcWjTw/r3rM+4cC6Xu0NbnrYaiRa2ZpqRQOuFoY6nmLj1k03Zy+g/AZE7yCMNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1b033f4b050f8171245edecfd9650fe72342914ba8e7fba7a43caa0e909290b","last_reissued_at":"2026-07-05T08:23:35.592568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:35.592568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Real-Time Voice Activity Detection Based On Lightweight Neural","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Di Wang, Jidong Jia, Pei Zhao","submitted_at":"2024-05-27T03:31:16Z","abstract_excerpt":"Voice activity detection (VAD) is the task of detecting speech in an audio stream, which is challenging due to numerous unseen noises and low signal-to-noise ratios in real environments. Recently, neural network-based VADs have alleviated the degradation of performance to some extent. However, the majority of existing studies have employed excessively large models and incorporated future context, while neglecting to evaluate the operational efficiency and latency of the models. In this paper, we propose a lightweight and real-time neural network called MagicNet, which utilizes casual and depth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16797","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/2405.16797/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":"2405.16797","created_at":"2026-07-05T08:23:35.592631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16797v1","created_at":"2026-07-05T08:23:35.592631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16797","created_at":"2026-07-05T08:23:35.592631+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGYDH5FQKD4B","created_at":"2026-07-05T08:23:35.592631+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGYDH5FQKD4BOESF","created_at":"2026-07-05T08:23:35.592631+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGYDH5FQ","created_at":"2026-07-05T08:23:35.592631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20885","citing_title":"SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z","json":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z.json","graph_json":"https://pith.science/api/pith-number/UGYDH5FQKD4BOESF5XWP3FSQ7Z/graph.json","events_json":"https://pith.science/api/pith-number/UGYDH5FQKD4BOESF5XWP3FSQ7Z/events.json","paper":"https://pith.science/paper/UGYDH5FQ"},"agent_actions":{"view_html":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z","download_json":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z.json","view_paper":"https://pith.science/paper/UGYDH5FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16797&json=true","fetch_graph":"https://pith.science/api/pith-number/UGYDH5FQKD4BOESF5XWP3FSQ7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/UGYDH5FQKD4BOESF5XWP3FSQ7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z/action/storage_attestation","attest_author":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z/action/author_attestation","sign_citation":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z/action/citation_signature","submit_replication":"https://pith.science/pith/UGYDH5FQKD4BOESF5XWP3FSQ7Z/action/replication_record"}},"created_at":"2026-07-05T08:23:35.592631+00:00","updated_at":"2026-07-05T08:23:35.592631+00:00"}