This paper discusses the improvement of speech recognition confidence scores in the presence of Magnetic Resonance Imaging (MRI) scanner noise using two parametric methods of signal enhancement. Our study deals with the comparison between the Non Linear Spectral Subtraction (NSS) with iterative overestimation and the SVD-based noise reduction techniques in enhancing medical content speech contaminated by MRI scanner noise. A speech recognition confidence score reflects how confident the recogniser is for the recognised utterance. This is important since errors in the presence of noise are more frequent and tend to make applications too cumbersome to use. The input signal is corrupted with MRI noise with varying Signal-to-Noise Ratio. As noise levels increase not only the Word Error Rate (WER) deteriorates but also the confidence score for each word decreases. It is proven experimentally that both techniques can improve the recognition performance of voice commands in order to voice control a MRI scanner. Two well-known speech enhancement techniques will be used in conjunction with the Continuous Speech Recognition system to quantify the impact of speech enhancement on confidence score accuracy. The recognition results show that both techniques improve the confidence accuracy, as expected, but the NSS outperformes SVD.