{ "timestamp": "2026-03-03T11:14:48.982664", "project": "MLAF - Multimodal Language Acquisition Framework", "institution": "Research collaboration \u2014 IIT Patna & IIT Kharagpur", "uasam_emission": { "subject_i": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "subject_you": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "subject_he": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "subject_she": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "subject_we": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "subject_they": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_want": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_eat": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_see": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_grab": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_drink": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_go": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "verb_stop": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "object_food": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "object_water": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "object_book": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "object_apple": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "object_ball": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 }, "object_house": { "silent": 0.25, "vocalization": 0.25, "speech_attempt": 0.25, "clear_speech": 0.25 } }, "uasam_note": "uniform prior (no audio data)", "gaze_emission": { "subject_i": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "subject_you": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "subject_he": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "subject_she": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "subject_we": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "subject_they": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_want": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_eat": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_see": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_grab": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_drink": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_go": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "verb_stop": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "object_food": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "object_water": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "object_book": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "object_apple": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "object_ball": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 }, "object_house": { "direct": 0.25, "averted": 0.25, "tracking_hand": 0.25, "tracking_face": 0.25 } }, "gaze_note": "uniform prior (no gaze data)", "fusion_weights": { "best_weights": { "w_visual": 0.6666666666666667, "w_acoustic": 0.16666666666666669, "w_gaze": 0.16666666666666669 }, "best_accuracy": 1.0, "grid_search_results": [ { "w_visual": 0.6666666666666667, "w_acoustic": 0.16666666666666669, "w_gaze": 0.16666666666666669, "accuracy": 1.0 }, { "w_visual": 0.5714285714285715, "w_acoustic": 0.14285714285714288, "w_gaze": 0.28571428571428575, "accuracy": 1.0 }, { "w_visual": 0.5, "w_acoustic": 0.125, "w_gaze": 0.37499999999999994, "accuracy": 1.0 }, { "w_visual": 0.5714285714285714, "w_acoustic": 0.2857142857142857, "w_gaze": 0.14285714285714285, "accuracy": 1.0 }, { "w_visual": 0.5, "w_acoustic": 0.25, "w_gaze": 0.25, "accuracy": 1.0 }, { "w_visual": 0.4444444444444444, "w_acoustic": 0.2222222222222222, "w_gaze": 0.33333333333333326, "accuracy": 1.0 }, { "w_visual": 0.5000000000000001, "w_acoustic": 0.375, "w_gaze": 0.12500000000000003, "accuracy": 1.0 }, { "w_visual": 0.44444444444444453, "w_acoustic": 0.33333333333333337, "w_gaze": 0.22222222222222227, "accuracy": 1.0 }, { "w_visual": 0.4, "w_acoustic": 0.3, "w_gaze": 0.3, "accuracy": 1.0 }, { "w_visual": 0.7142857142857143, "w_acoustic": 0.14285714285714288, "w_gaze": 0.14285714285714288, "accuracy": 1.0 }, { "w_visual": 0.625, "w_acoustic": 0.125, "w_gaze": 0.25, "accuracy": 1.0 }, { "w_visual": 0.5555555555555556, "w_acoustic": 0.11111111111111113, "w_gaze": 0.33333333333333337, "accuracy": 1.0 }, { "w_visual": 0.625, "w_acoustic": 0.25000000000000006, "w_gaze": 0.12500000000000003, "accuracy": 1.0 }, { "w_visual": 0.5555555555555556, "w_acoustic": 0.22222222222222227, "w_gaze": 0.22222222222222227, "accuracy": 1.0 }, { "w_visual": 0.5, "w_acoustic": 0.2, "w_gaze": 0.3, "accuracy": 1.0 }, { "w_visual": 0.5555555555555556, "w_acoustic": 0.3333333333333333, "w_gaze": 0.11111111111111112, "accuracy": 1.0 }, { "w_visual": 0.5, "w_acoustic": 0.3, "w_gaze": 0.2, "accuracy": 1.0 }, { "w_visual": 0.45454545454545453, "w_acoustic": 0.2727272727272727, "w_gaze": 0.2727272727272727, "accuracy": 1.0 }, { "w_visual": 0.75, "w_acoustic": 0.12500000000000003, "w_gaze": 0.12500000000000003, "accuracy": 1.0 }, { "w_visual": 0.6666666666666667, "w_acoustic": 0.11111111111111113, "w_gaze": 0.22222222222222227, "accuracy": 1.0 }, { "w_visual": 0.6, "w_acoustic": 0.1, "w_gaze": 0.3, "accuracy": 1.0 }, { "w_visual": 0.6666666666666666, "w_acoustic": 0.22222222222222224, "w_gaze": 0.11111111111111112, "accuracy": 1.0 }, { "w_visual": 0.6, "w_acoustic": 0.2, "w_gaze": 0.2, "accuracy": 1.0 }, { "w_visual": 0.5454545454545454, "w_acoustic": 0.18181818181818182, "w_gaze": 0.2727272727272727, "accuracy": 1.0 }, { "w_visual": 0.6000000000000001, "w_acoustic": 0.30000000000000004, "w_gaze": 0.10000000000000002, "accuracy": 1.0 }, { "w_visual": 0.5454545454545455, "w_acoustic": 0.27272727272727276, "w_gaze": 0.18181818181818185, "accuracy": 1.0 }, { "w_visual": 0.5, "w_acoustic": 0.25, "w_gaze": 0.25, "accuracy": 1.0 } ] } }