No abstract

No abstract

No abstract

This paper implements and compares the performance of a number of techniques proposed for improving the accuracy of Automatic Speech Recognition (ASR) systems. As ASR that uses only speech can be contaminated by environmental noise, in some applications it may be improve performance to employ Audio-Visual Speech Recognition (AVSR), in which recognition uses both audio information and mouth movements obtained from a video recording of the speaker's face region. In this paper, model validation techniques, namely the holdout method, leave-one-out cross validation and bootstrap validation, are implemented to validate the performance of an AVSR system as well as to provide a comparison of the performance of the validation techniques themselves. A new speech data corpus is used, namely the Loughborough University Audio-Visual (LUNA-V) dataset that contains 10 speakers with five sets of samples uttered by each speaker. The database is divided into training and testing sets and processed in manners suitable for the validation techniques under investigation. The performance is evaluated using a range of different signal-to-noise ratio values using a variety of noise types obtained from the NOISEX-92 dataset.

Existing researchers for rubeosis iridis disease focused on image enhancement as a collective group without considering the multi-contrast of the images. In this paper, the pre-enhancement process was proposed to improve the quality of iris images for rubeosis iridis disease by separating the image into three groups; low, medium and high contrast. Increment, decrement and maintenance of the images' original contrast were further operated by noise reduction and multi-contrast manipulation to attain the best contrast value in each category for increased compatibility prior subsequent enhancement. As a result, this study proved that there have three rules for the contrast modification method. Firstly, the histogram equalization (HE) filter and increasing the image contrast by 50% will achieve the optimum value for the low contrast category. Experimental revealed that HE filters successfully increase the luminance value before undergoing the contrast modification method. Secondly, reducing the 50% of the image contrast to achieve the optimum value for the high contrast category. Finally, the image contrast was maintained for the middle contrast category to optimise contrast. The mean square error (MSE) and peak signal-to-noise ratio (PSNR) of the outputs were then calculated, yielding an average of 18.25 and 28.87, respectively.