 This paper compares several deep learning techniques and acoustic features in order to assess the severity level of dysarthria. The authors found that the best results were achieved by using a combination of MFCC-based iVector representations and DNN models. This system was able to achieve an accuracy of 93.97% under the speaker-dependent scenario and 49.22% under the speaker-independent scenario. This article was authored by Amlu Anijashi and Rajiv Rajan.