Abstract This paper presents an approach to recognition of human emotions from speech. Seven emotions are recognized: anger, fear, sadness, happiness, boredom, disgust and neutral. The approach is applied on a speech database, which consists of simulated and annotated utterances. First, numerical features are extracted from the sound database by using audio feature extractor. Next, the extracted features are standardized. Then,... This paper presents an approach to recognition of human emotions from speech. Seven emotions are recognized: anger, fear, sadness, happiness, boredom, disgust and neutral. The approach is applied on a speech database, which consists of simulated and annotated utterances. First, numerical features are extracted from the sound database by using audio feature extractor. Next, the extracted features are standardized. Then, feature selection methods are used to select the most relevant features. Finally, a classification model is trained to recognize the emotions. Three classification algorithms are tested, with SVM yielding the highest accuracy of 89% and 82% using the 10 fold cross-validation and Leave-One- Speaker-Out techniques, respectively. “Sadness” is the emotion which is recognized with highest accuracy. Read More Read Less

Abstract Data exploration techniques aim to efficiently and effectively guide users towards interesting data within massive, complex data. Being one of those techniques, query refinement goal is to automatically refine a user’s query so that its result satisfies a certain constraint. In this paper, we focus on time series correlation as a constraint for refinement such that the result of a... Data exploration techniques aim to efficiently and effectively guide users towards interesting data within massive, complex data. Being one of those techniques, query refinement goal is to automatically refine a user’s query so that its result satisfies a certain constraint. In this paper, we focus on time series correlation as a constraint for refinement such that the result of a query is a pair of two subsequence time series. Differently than most existing works, we make use of the deviation from a correlation constraint as an objective to minimize in our problem. Moreover, we include users preferences as an objective to maximize in proportion to users input queries. The combination of these two objectives are prevalent in applications where users seek time series subsequences that exhibit a certain correlation value range and are close from their initial queries. Towards finding the optimal query satisfying these objectives, we propose an efficient computationalcentric algorithm and an innovative I/O-centric algorithm as well. We experimentally validate the efficiency and effectiveness of our proposed algorithms using real and synthetic data compared to recently proposed correlation-based subsequence search algorithms. Read More Read Less

Abstract Palm Leaf Manuscripts are historical heritage of India. They store within themselves the unexplored treasures of knowledge. Though the age of these leaves is about 300yrs, the tradition of guru-shisya relationship has made their life much beyond. The knowledge in them covers all aspects of life. Be it religious beliefs, literature, science, mathematics, or any other. However, due to discontinuation... Palm Leaf Manuscripts are historical heritage of India. They store within themselves the unexplored treasures of knowledge. Though the age of these leaves is about 300yrs, the tradition of guru-shisya relationship has made their life much beyond. The knowledge in them covers all aspects of life. Be it religious beliefs, literature, science, mathematics, or any other. However, due to discontinuation of practise of copying their content on fresh leaves, they now possess a fragile life which needs to be preserved at the earliest. The modern means of digitization can help in their preservation. With computer technology penetrating every aspect of life, we can exploit information retrieval algorithms to help build a system which can dig into the ocean of knowledge from these manuscripts. This paper is an attempt to popularize information retrieval from palm leaf manuscripts among computer scientists to make available the guidance of our age old heritage in shaping our future. Read More Read Less

Abstract This paper compares different modes of competitive and collaborative play for co-located computer supported English vocabulary learning. To do this we have developed a video-game for learning vocabulary than can be played by two players sitting together by either working together and collaborating to improve their score or competing against each other to see who can achieve the best score.... This paper compares different modes of competitive and collaborative play for co-located computer supported English vocabulary learning. To do this we have developed a video-game for learning vocabulary than can be played by two players sitting together by either working together and collaborating to improve their score or competing against each other to see who can achieve the best score. We evaluated these different collaborative and competitive game modes by asking ninety-six participants to complete a test before and after playing the games. Our participants were also asked to fill out a questionnaire and take part in a structured interview after playing the game. Results from this evaluation reveal that collaborative play is more effective than competitive play for helping students to achieve learning objectives, but neither type of play is effective as traditional learning using vocabulary leaning cards. Collaborative play was found to give around 56% the improvement of traditional learning with competitive play giving around 7%. Collaborative play is also preferred by most students involved in the study, and the participants in our study considered that either type of game could play an important role to supplement traditional learning in a more relaxed and sociable environment. Read More Read Less