Abstract-This paper describes speech signal modeling techniques which are suited to high performance and robust isolated word recognition. In this study, a speech recognition system is presented, specifically an isolated spoken Malay word recognizer which uses spontaneous and formally speeches collected from Parliament of Malaysia. Currently the vocabulary is limited to 25 words that can be pronounced exactly as it written and controls the distribution of the vocalic segments. The speech segmentation task is achieved by adopted energy based parameter and zero crossing rate measure with modification to better locates the beginning and ending points of speech from the spoken words. The training and recognition processes are realized by using Multi-layer Perceptron (MLP) Neural Networks with two-layer network configurations that are trained with stochastic error back-propagation to adjust its weights and biases after presentation of every training data. The Melfrequency Cepstral Coefficients (MFCCs) has been chosen as speech extraction approach from each segmented utterance as characteristic features for the word recognizer. Recognition results showed that the performance of the two-layer networks increased as the numbers of hidden neurons increased. The best network structures average classification rate is 84.731% with (150-25) configuration. Implementation results also showed that the conjugate gradient (CG) algorithm was more accurate and reliable than the Levenberg-Marquardt (LM) algorithm for the network complexities and data size considered in this study.
A huge amount of data is generated every minute for social networking and content sharing via Social media sites that can be in a form of structured, unstructured or semi-structured data. One of the largest used social media sites is Twitter, where each and every day millions of data generated in the form of unstructured tweets. Tweets or opinions of the people can be used to extract sentiments of the people. Sentiment analysis is beneficial for organizations to improve their products and make required changes on demand to increase their profit. In this paper, three machine learning algorithms Support Vector Machine (SVM), Decision Trees (DT), and Naive Bayes (NB) for classifying sentiments of twitters data. The purpose of this research is to compare the outcomes of these algorithms to identify best machine learning method which gives most accurate and efficient results for classifying twitter data. Our experimental result shows that same preprocessing methods on a different dataset affect similarly the classifiers performance. After analyzing the results it is observed that SVM provides 64.96%, 71.26% and 91.25% precision which is better than other two algorithms. Also, overall Recall and F-measure rate of SVM is greater than NB and DT for three datasets. However, it is important to further study current available preprocessing techniques that help us to improve results of various classifiers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations 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.