{"id":"W4408113760","doi":"10.1121/10.0036052","title":"Voice assistant technology continues to underperform on children's speech","year":2025,"lang":"en","type":"article","venue":"JASA Express Letters","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001845566,0.0002117905,0.0002699225,0.0005264303,0.0001418111,0.0002052656,0.001341733,0.0001253144,0.000004953232],"category_scores_gemma":[0.000104699,0.000192311,0.00007911486,0.0007942824,0.0000601215,0.000185749,0.0003291501,0.0002213121,0.000364805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105088,"about_ca_system_score_gemma":0.00004102449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009322399,"about_ca_topic_score_gemma":0.00001471614,"domain_scores_codex":[0.9983191,0.0000522927,0.0002733661,0.0006010279,0.0002844227,0.000469795],"domain_scores_gemma":[0.9986469,0.0001122272,0.0000749044,0.001017881,0.00004837124,0.00009975729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001372553,0.0002967088,0.01994817,0.00005217538,0.0002266297,0.000233041,0.000775088,0.0002851322,0.2094169,0.06723086,0.6348268,0.06657126],"study_design_scores_gemma":[0.004006321,0.0006352176,0.09067627,0.0009303215,0.00004546736,0.00007833913,0.0002428247,0.0008321577,0.6018345,0.005362512,0.2934414,0.001914673],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6644353,0.0001429081,0.2632231,0.05655684,0.002374051,0.0009129934,0.00001935496,0.0008680948,0.01146733],"genre_scores_gemma":[0.9670287,0.000002297382,0.01430158,0.01744313,0.0001870999,0.00007599775,0.000007684254,0.00001343683,0.000940041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3924176,"threshold_uncertainty_score":0.7842214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00566815040736642,"score_gpt":0.2305283615674443,"score_spread":0.2248602111600779,"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."}}