This paper investigates the contribution of formants and prosodic features such as pitch and energy in Arabic speech recognition under real-life conditions. Our speech recognition system based on Hidden Markov Models (HMMs) is implemented using the HTK Toolkit. The frontend of the system combines features based on conventional Mel-Frequency Cepstral Coefficient (MFFC), prosodic information and formants. The experiments are performed on the ARADIGIT corpus which is a database of Arabic spoken words. The obtained results show that the resulting multivariate feature vectors, in noisy environment, lead to a significant improvement, up to 27%, in word accuracy relative the word accuracy obtained from the state-of-the-art MFCCbased system.
Host-overloading detection is an important phase in the dynamic Virtual Machines (VMs) consolidation process. Using machine learning to predict the future workload on a host, is a very promising technique to avoid the overload host situation. In this work, we propose a novel approach for overloaded hosts detection, based on neural network and Markov model. The neural network is trained on a workload data set composed of VMs CPU-utilization history. The trained model is then used to predict the future usage for a given Physical Machine(PM), by summing up the predicted utilization of all its VMs. The confidence of this prediction is measured through a dynamic safety parameter, based on Markov model. The obtained results show that our approach outperforms the state of the art algorithms such as: MAD, IQR and LRR.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations鈥揷itations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.