{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GQLVZV55WRDDQ75PEK4Y4DD3PI","short_pith_number":"pith:GQLVZV55","schema_version":"1.0","canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","source":{"kind":"arxiv","id":"2506.01365","version":1},"attestation_state":"computed","paper":{"title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chowdam Venkata Kumar, Kumud Tripathi, Pankaj Wasnik","submitted_at":"2025-06-02T06:47:42Z","abstract_excerpt":"Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that simple fusion techniques, particularly addition, outperform CA in both accuracy and efficiency. Fusio"},"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":"2506.01365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T06:47:42Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"1a12de5de738697bed2b019dac4e636918f7ddd09fa7c86a4fe0502ced262fd0","abstract_canon_sha256":"ec49325e24696e7758a0afd9d7ce1624539aaf2f42e154940f410b9bc2e6237e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:12.258156Z","signature_b64":"xc8rBegkEqNQZwbgGpdKnjos/1P2AN033QmJFuxIUiTAkzroSkaXB80IqaxjREbwrI/7qRBwhpZ2pp0w/NTcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","last_reissued_at":"2026-07-05T11:14:12.257667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:12.257667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chowdam Venkata Kumar, Kumud Tripathi, Pankaj Wasnik","submitted_at":"2025-06-02T06:47:42Z","abstract_excerpt":"Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that simple fusion techniques, particularly addition, outperform CA in both accuracy and efficiency. Fusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01365","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/2506.01365/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":"2506.01365","created_at":"2026-07-05T11:14:12.257730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01365v1","created_at":"2026-07-05T11:14:12.257730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01365","created_at":"2026-07-05T11:14:12.257730+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQLVZV55WRDD","created_at":"2026-07-05T11:14:12.257730+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQLVZV55WRDDQ75P","created_at":"2026-07-05T11:14:12.257730+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQLVZV55","created_at":"2026-07-05T11:14:12.257730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01365","citing_title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI","json":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI.json","graph_json":"https://pith.science/api/pith-number/GQLVZV55WRDDQ75PEK4Y4DD3PI/graph.json","events_json":"https://pith.science/api/pith-number/GQLVZV55WRDDQ75PEK4Y4DD3PI/events.json","paper":"https://pith.science/paper/GQLVZV55"},"agent_actions":{"view_html":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI","download_json":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI.json","view_paper":"https://pith.science/paper/GQLVZV55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01365&json=true","fetch_graph":"https://pith.science/api/pith-number/GQLVZV55WRDDQ75PEK4Y4DD3PI/graph.json","fetch_events":"https://pith.science/api/pith-number/GQLVZV55WRDDQ75PEK4Y4DD3PI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/action/storage_attestation","attest_author":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/action/author_attestation","sign_citation":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/action/citation_signature","submit_replication":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/action/replication_record"}},"created_at":"2026-07-05T11:14:12.257730+00:00","updated_at":"2026-07-05T11:14:12.257730+00:00"}