Sharif Digital Repository

In recent years, deep neural networks have achieved significant improvements in the field of automatic text summarization by using neural sequence architectures. However,the results of these improvements are more tangible in the production of short summaries (a few words or single sentences). In the field of producing long (multisentence) abstracts, the presented models suffer from several issues; These models produce the details of the events incorrectly and tend to generate the phrases been produced before repeatedly. The wording from the output of these models is very close to the original text. Also, the metrics used to evaluate the quality of produced summaries do not have the ability... 

Sparse-view computed tomography (CT) is recently proposed as a promising method to speed up data acquisition and alleviate the issue of CT high-dose delivery to patients. However, traditional reconstruction algorithms are time-consuming and suffer from image degradation when faced with sparse-view data. To address this problem, we propose two new frameworks based on deep learning (DL) that can quickly produce high-quality CT images from sparsely sampled projections and is able for clinical use. Our first DL-based proposed model is based on the convolution, and residual neural networks in a parallel manner, named the parallel residual neural network (PARS-Net). Besides, our proposed PARS-Net... 

Edge AI, an emerging approach, aims to provide AI services by utilizing computing resources at the edge of the network rather than relying on cloud servers. This offers advantages such as reduced latency, improved efficiency, privacy preservation, and resilience. Model inference at the edge is a crucial area in this domain, where a trained model is deployed to an edge server or user device. Deploying models on resource constrained edge devices poses key challenges, including optimizing and compressing the models to fit within limited computational and memory constraints. Additionally, ensuring the deployed model can perform inference within required time constraints is critical. Research... 

The problem of separation of audio sources is one of the oldest issues raised in the field of audio processing, which has been studied for more than half a century. The main focus of recent research in this field has been on improving the sound quality resulting from the separation of sound sources with the help of deep neural networks. This is despite the fact that in most applications of audio source separation, such as the application of meeting transcription, we do not need the separated audio of people. Rather, we need a pipeline of converting overlapping speech to text, which, by receiving the audio in which several people have spoken, outputs the text spoken by the people present in...