{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NLAYI57DJPLZNHJRI6EFGTVXYH","short_pith_number":"pith:NLAYI57D","schema_version":"1.0","canonical_sha256":"6ac18477e34bd7969d314788534eb7c1e05392a6792e6b6628ba94ce301c150e","source":{"kind":"arxiv","id":"2102.07445","version":2},"attestation_state":"computed","paper":{"title":"On training targets for noise-robust voice activity detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ivan Tashev, Sebastian Braun","submitted_at":"2021-02-15T10:37:14Z","abstract_excerpt":"The task of voice activity detection (VAD) is an often required module in various speech processing, analysis and classification tasks. While state-of-the-art neural network based VADs can achieve great results, they often exceed computational budgets and real-time operating requirements. In this work, we propose a computationally efficient real-time VAD network that achieves state-of-the-art results on several public real recording datasets. We investigate different training targets for the VAD and show that using the segmental voice-to-noise ratio (VNR) is a better and more noise-robust trai"},"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":"2102.07445","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-02-15T10:37:14Z","cross_cats_sorted":[],"title_canon_sha256":"f8d70a1a798be13e14bf0220bccbc5ab5dd06752c67ca838102ece59ba991835","abstract_canon_sha256":"bedf74c00f9fbeee342e3694896ad98d2840d45d54e04391cd733b47c17e3f92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:31.409428Z","signature_b64":"Vcwghr46A7/YGwALc9x+A6p4LSVw73tTyTuPuapzSvVRyW5z+6ffEC3ugDXK0A/uPi0wbcKqqRXgZTUtqnZRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac18477e34bd7969d314788534eb7c1e05392a6792e6b6628ba94ce301c150e","last_reissued_at":"2026-07-05T02:41:31.408967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:31.408967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On training targets for noise-robust voice activity detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ivan Tashev, Sebastian Braun","submitted_at":"2021-02-15T10:37:14Z","abstract_excerpt":"The task of voice activity detection (VAD) is an often required module in various speech processing, analysis and classification tasks. While state-of-the-art neural network based VADs can achieve great results, they often exceed computational budgets and real-time operating requirements. In this work, we propose a computationally efficient real-time VAD network that achieves state-of-the-art results on several public real recording datasets. We investigate different training targets for the VAD and show that using the segmental voice-to-noise ratio (VNR) is a better and more noise-robust trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07445","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/2102.07445/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":"2102.07445","created_at":"2026-07-05T02:41:31.409030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07445v2","created_at":"2026-07-05T02:41:31.409030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07445","created_at":"2026-07-05T02:41:31.409030+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLAYI57DJPLZ","created_at":"2026-07-05T02:41:31.409030+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLAYI57DJPLZNHJR","created_at":"2026-07-05T02:41:31.409030+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLAYI57D","created_at":"2026-07-05T02:41:31.409030+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":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH","json":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH.json","graph_json":"https://pith.science/api/pith-number/NLAYI57DJPLZNHJRI6EFGTVXYH/graph.json","events_json":"https://pith.science/api/pith-number/NLAYI57DJPLZNHJRI6EFGTVXYH/events.json","paper":"https://pith.science/paper/NLAYI57D"},"agent_actions":{"view_html":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH","download_json":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH.json","view_paper":"https://pith.science/paper/NLAYI57D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07445&json=true","fetch_graph":"https://pith.science/api/pith-number/NLAYI57DJPLZNHJRI6EFGTVXYH/graph.json","fetch_events":"https://pith.science/api/pith-number/NLAYI57DJPLZNHJRI6EFGTVXYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH/action/storage_attestation","attest_author":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH/action/author_attestation","sign_citation":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH/action/citation_signature","submit_replication":"https://pith.science/pith/NLAYI57DJPLZNHJRI6EFGTVXYH/action/replication_record"}},"created_at":"2026-07-05T02:41:31.409030+00:00","updated_at":"2026-07-05T02:41:31.409030+00:00"}