{"id":"W4390481136","doi":"10.1109/humanoids57100.2023.10375198","title":"An Audio-Video Sensor Fusion Framework To Augment Humanoid Capabilities For Identifying And Interacting With Human Conversational Partners","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Humanoid robot; Computer science; Human–computer interaction; Robot; Sensor fusion; Human–robot interaction; Artificial intelligence; Computer vision","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":[0.0005775088,0.0007995021,0.0004084175,0.0004909671,0.000325082,0.0005710503,0.0007141536,0.0006248408,0.003898998],"category_scores_gemma":[0.0008901496,0.0001876698,0.0003502484,0.0002603313,0.0003634904,0.0008193893,0.00122708,0.0005816203,0.0009325774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002549641,"about_ca_system_score_gemma":0.0005044037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002410901,"about_ca_topic_score_gemma":0.004253365,"domain_scores_codex":[0.9997193,0.00005995646,0.00001114603,0.00007688958,0.00009947064,0.00003310712],"domain_scores_gemma":[0.9997799,0.00005987119,0.00002223334,0.00002626432,0.00008408823,0.00002751233],"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":[0.0008050422,0.0003209778,0.001704403,0.0004261206,0.0001250677,0.000680759,0.0009018238,0.04077994,0.401695,0.007124926,0.005414902,0.5400211],"study_design_scores_gemma":[0.00008466597,0.001520584,0.007321582,0.0001167896,0.0001417812,0.001802942,0.0006934519,0.8056203,0.1285914,0.0183936,0.03555874,0.0001541478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02254484,0.0005270432,0.9714078,0.0001613598,0.00009608717,0.0001187842,0.0001443175,0.00193178,0.003068042],"genre_scores_gemma":[0.4833448,0.0003842352,0.5105159,0.0001721264,0.00007231934,0.000185092,0.0003289984,0.00009810764,0.004898489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003898998,"threshold_uncertainty_score":0.01304346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05219884197355233,"score_gpt":0.3632951692169185,"score_spread":0.3110963272433661,"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."}}