this experimental study examined the effectiveness of using focused and unfocused tasks on iranianintermediate efl learners’ performance in producing noun, adjective, and adverb clauses. in addition,the aim of this study was to explore the effects of form-focused instruction and the feedback studentsreceived from their teacher after doing focused grammar tasks. data consisted of the scores ofth...

0

iii   this study was an attempt to determine the effect of task-based approach vs. traditional approach on the narrative and expository writing of the iranian efl learners. there were two control groups as well as two experimental ones in the current study. in the two control groups namely g1 and g2 narrative and expository writing were taught respectively using the traditiona...

Automatic speech recognition systems usually rely on spectral-based features, such as MFCC of PLP. These features are extracted based on prior knowledge such as, speech perception or/and speech production. Recently, convolutional neural networks have been shown to be able to estimate phoneme conditional probabilities in a completely data-driven manner, i.e. using directly temporal raw speech si...

Traditional automatic speech recognition (ASR) systems usually get a sharp performance drop when noise presents in speech. To make a robust ASR, we introduce a new model using the multi-task learning deep neural networks (MTL-DNN) to solve the speech denoising task in feature level. In this model, the networks are initialized by pre-training restricted Boltzmann machines (RBM) and fine-tuned by...

In this paper we address the important task of automated discovery of speech act categories in dialogue-based, multi-party educational games. Speech acts are important in dialogue-based educational systems because they help infer the student speaker’s intentions (the task of speech act classification) which in turn is crucial to providing adequate feedback and scaffolding. A key step in the spe...