Artificial Neural Network based audio reinforcement for computer assisted rote learning

The dual-channel assumption of the cognitive theory multimedia learning suggests that importing a large amount information through single (visual or audio) channel overloads channel, causing partial loss information, while it simultaneously multiple channels relieves burden on them and leads to registration larger information. In light such knowledge, this study investigates possibility reinforcing visual stimuli with audio for supporting e-learners in memorization tasks. Specifically, we consider three kinds material two partially reinforce each kind an arbitrary way. series experiments, determine particular type audio, which offers highest improvement material. Our work stands out as being first investigating differences memory performance relation different combinations content stimulus. key findings from experiments are: (i) E-learning is more effective refreshing rather than studying scratch, (ii) Non-informative suited verbal content, whereas informative better numerical (iii) Constant triggering degrades thus should be handled care. Based these findings, develop ANN-based estimator proper moment (i.e. when estimated declining) carry follow-up testing integrated framework. contributions involve determination most type, estimation deterioration based learners’ interaction logs, proposal auditory reinforcement. We believe constitute encouraging evidence can enhanced content-aware incorporation.