{"id":"W4415524446","doi":"10.1109/mlsp62443.2025.11204268","title":"Tiny Noise-Robust Voice Activity Detector for Voice Assistants","year":2025,"lang":"","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Voice activity detection; Background noise; Noise (video); Detector; Human voice; Speech enhancement; SIGNAL (programming language)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005880906,0.001022155,0.001036183,0.0007379892,0.0003893735,0.0008840162,0.001574458,0.00104597,0.001853155],"category_scores_gemma":[0.001875959,0.0003798764,0.000638437,0.0003279649,0.0003600286,0.0009895901,0.001223671,0.0009345543,0.002213542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004450752,"about_ca_system_score_gemma":0.0004142053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006419008,"about_ca_topic_score_gemma":0.0009873934,"domain_scores_codex":[0.9991127,0.0001276148,0.00005044459,0.0002688748,0.0003609851,0.00007938492],"domain_scores_gemma":[0.9994606,0.0001667332,0.00004133306,0.00008873081,0.0001905372,0.00005208128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009562154,0.0002322256,0.002299628,0.0002849514,0.0001400362,0.0003140022,0.0001023363,0.01589865,0.2569016,0.002620584,0.005321072,0.7149287],"study_design_scores_gemma":[0.00006802339,0.0005043924,0.001810882,0.00004047096,0.0001044502,0.001346422,0.00005589473,0.741357,0.2343533,0.002673311,0.0176147,0.00007126771],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01521217,0.0008029527,0.9779683,0.00009589538,0.0002242578,0.00007800552,0.0001075599,0.004321713,0.001189053],"genre_scores_gemma":[0.4719081,0.0006314791,0.517884,0.0007241293,0.000251402,0.0002173739,0.0006862846,0.000291503,0.007405689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001853155,"threshold_uncertainty_score":0.006199479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03097398684967214,"score_gpt":0.2877127385676779,"score_spread":0.2567387517180058,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}