Sharif Digital Repository

Speech enhancement in noisy environments improves the quality and intelligibility of speech and reduces communication fatigue. High performance speech enhancement models are based on Bayesian estimation models, requiring estimations of the parameters of the functions that describe the likelihood and the prior distributions of the signal and noise processes. Two Bayesian speech enhancement models which are used in this thesis are Bayesian-Kalman filter and Bayesian MAP estimation.In real time applications including VoIP, in addition to additive noise, packet loss or packet delays might also occur. In real time communications the receiver terminal replaces silence for the duration of lost... 

The objective of this thesis is to develop a speech enhancement technique that can be applied for enhancement of speech degraded by additive background noise. The important aim of speech enhancement is to get better result after transmission at the receiver side. Additive noise such as White Gaussian Noise, Street Noise, Babble Noise, etc, is one of the speech enhancement problems degrading the intelligibility and quality of the signal. The important applications for speech enhancement are VOIP, Telephone services, mobile telephony, hands free voice control, communication between pilot cockpit, etc. Wiener filters are the mostly used techniques to reduce the uncorrelated additive noise with... 

In speech processing, reflections of sound wave in a bounded space are considered as speech reverberation. Although for musical instruments and their related recording devices these reflections are useful, however, some other applications face serious problems receiving them along with speech signal. Reverberation causes speech degradation and intelligibility as well as highly quality reduction. Dereverberation algorithms are essential for Automatic Speech Recognition (ASR), telecommunication and hearing aid devices, which are some of the mostly used applications. While dereverberation itself is a challenging problem, dereverberate a speech signal recorded only by one microphone (channel)... 

Nowadays financial and business jobs without new technologies and new methods to manage are not that much useful. Managers are searching for all new methods in different areas for improving their profit, quality of services or increasing number of their customers. Because of this, they would check some ways to prove their issues. But the point is that they should have a great view about their products, customers and generally their own shop. One of the perfect methods to present the form and relation between their favorite factors is complex network. With complex network they can have perfect sight about their system. Also, with some remarkable and noticeable ways they can categorize their... 

In process of making prosthetic limb, each of the prosthetic limbs must be costume fitted and built since each amputation of the patient is unique. The design and fabrication process of artificial limb consists of several different steps and begins with a precise measurement process that will be used to design the prosthetic limb. If possible, a prosthetist begins taking measurements before the patient's limb is even amputated, so that the fabrication process can get started. Today, much research which has been done in Augmented Reality and 3D scanning technologies shows that these technologies can help people with disabilities to have better experience in their life by using them in... 

This thesis proposes a novel method for enhancing the image signal based on compressed sensing. Compressed sensing, as a new rapidly growing research field, promises to effectively recover a sparse signal at the rate of below Nyquist rate. This revolutionary technology strongly relies on the sparsity of the signal and incoherency between sensing basis and representation basis. Exact recovery of a sparse signal will be occurred in a situation that the signal of interest sensed randomly and the measurements are also taken based on sparsity level and log factor of the signal dimension. In this research, compressed sensing method is proposed to reduce the noise and reconstruct the image signal.... 

Radar is a type of active remote sensing instrument that is used to create images of an object, such as a landscape. Synthetic Aperture Radar or SAR is another type of radar which is typically mounted on a moving platform such as an aircraft or a spacecraft and uses the motion of the antenna over the target region to provide finer spatial resolution than is possible with conventional beam-scanning radars. In fact SAR is an advanced form of Side-Looking Airborne Radar (SLAR). The movement of SAR antenna acts as another form of aperture; this aperture combined with the physical aperture of the antenna creates a large "synthetic" antenna aperture (the "size" of the antenna) which enables higher... 

This thesis aims to develop speech enhancement methods in the presence of additive noise, packet loss and band-limitation of speech signal. Noise reduction of speech improves the perceived quality and intelligibility. High performance noise reduction methods are based on Bayesian methods requiring estimates of the parameters of the functions that describe the likelihood and the prior distributions of the signal and noise processes. The Bayesian noise reduction method which is used in this thesis is Kalman filter.In packet-based speech processing applications such as Internet and Voice over Internet Protocol (VoIP), it is possibly expected that some packets during signal transmission are... 

Decades ago, scientists and researchers found out proteins are not function isolated and act in multi protein complexes as complex networks. So, they started to study about proteins and their interaction in the term of protein-protein interaction, therefore, the number of publication in this field grows rapidly. This large amount of published articles (in scientific journals or web pages or books) are unstructured and it is hard to classify them manually. Also, study and read all of these documents is difficult for one person. Hence, it’s better to find a way which could help scientists and researcher to study these unstructured or semi-structured information more easily. The best way to... 

In this thesis, the Artificial Neural Networks (ANN) will be used in Automatic Speech Recognition (ASR) instead of Hidden Markov Models (HMM). Hidden Markov Model is one of the most dominant Bayesian network technologies and is the most successful model in current ASR systems. However, excessive training time is a major issue in speech recognition based on Hidden Markov Model (HMM). This thesis presents an Artificial Neural Network language model for human speech by mapping the spectral features of speech namely the formants, cepstrum (Mel-Frequency Cepstral Coefficients (MFCCs)) and Power Spectral Density (PSD) as features of samples of specific words into a discrete vector space. The... 

Digital Signal Processing (DSP) is used in a wide range of applications such as high-definition TV, digital audio, multimedia, digital cameras, radar, sonar detectors, biomedical imaging, global positioning, digital radio, speech recognition and etc. These applications can be implemented by either DSP processors or FPGA technology. Digital Signal Processors are microprocessors specifically designed to handle Digital Signal Processing tasks. These devices have seen a tremendous growth in the last decade, finding use in everything from cellular telephones to advanced scientific instruments. On the other hand, the rise of FPGA in the signal processing realm could be assigned to hardware to... 

Medical images contain human body pictures and are widely used for diag-nosis and surgical purposes. Compression is needed for medical images for some applications such as profiling a patient's data or transmission systems. Due to the importance of the information of medical images, lossless or visually lossless compression is preferred. Lossless compression mainly consists of transformation and encoding steps. On the other hand, hardware implementation of lossless compression algorithm accelerates real time tasks such as online diagnosis and telemedicine. Lossless JPEG, JPEG-LS and lossless version of JPEG2000 are few well known methods for lossless compression. In this thesis, we introduce... 

Pitch or fundamental frequency is one of the components of speech production. Pitch detection is the process of determining the period of the vocal cords closure or in other words, the time duration of one glottal closing, opening and returning phase. There are different algorithms for pitch detection purposes, each of which has some advantages and disadvantages. Pitch detection algorithms can be classified into event pitch detection and non-event pitch detection. Dyadic wavelets transform is an example of event pitch detection. Modified higher order moment, which is based on the Autocorrelation function, is non-event pitch detection. Dyadic wavelets transform is a fast and simple pitch... 

In real-time packet-based communication systems one major problem is misrouted or delayed packets which result in degraded perceived voice quality. If some speech packets are not available on time, the packet is known as lost packet. The easiest task of a network terminal receiver is to replace silence for the duration of lost speech segments. In a high quality communication system in order to avoid quality reduction due to packet loss a suitable method and/or algorithm is needed to replace the missing segments of speech.There are several methods which have been proposed to reduce the effect of packet loss such as Waveform Substitution, High Order Autoregressive, Linear Prediction (LP),... 

Structural Health Monitoring (SHM) means to give a diagnosis of the “state” of the subjects. Small leaks along the entire lengths of oil pipelines are detected and located by monitoring.Nowadays health monitoring of pipeline in water, gas, oil and chemical industry has been the focus of researchers. This is due to the fact that leak accidents may cause great economic problems to human resources as well as extreme environmental pollution. This project focuses on a visual and photographic observation system as leakage detection to monitor long range pipelines. In this system, several cameras with overlapping views are located along the entire lengths of pipelines. We are using digital cameras... 

Complex Networks are everywhere, many complex systems can be represented as networks, such as the power grid, the road network, the airline network and the Protein-protein interaction network, delivery and distribution networks, and telephone networks. A fundamental issue concerning complex networks is the robustness of the overall system to the failure of its constituent parts. The robustness of networks against failure, targeted attacks to individuals’ components, and the impact on the performance of the system has become an important issue for practical reasons in the last few years. The failures attacks or errors on networks are not limited to the deletion of vertex, for common... 

Developing of space technology requires a realization of deep space scientific missions such as Mars exploration. NASA enterprises have outlined scientific challenges for success and reliable transfer of data for new design and version of space network architecture.These communications requires high bit rate for autonomous operations and also have several different limitations. These type of communications set as a network that is called IPN. One of the important challenges in IPN is reliability. As regard there are difference challenge in space communication that TCP is not capable to address Long propagation delay, asymmetric bandwidth and etc. Therefore we require new protocols that will... 

Detection and classification of arrhythmia is important especially for patients in Emergency care units. Early diagnosis of cardiac arrhythmia makes it possible to choose appropriate anti arrhythmic drugs, and is thus very important for improving arrhythmia therapy. Computer-Assisted Diagnostic (CAD) Systems are used in recent decades in which extracted features and classifiers are the most important factor. In this project, we try to focus on both of these two major factors in heart arrhythmia classification using HRV signal. Therefore, in this project, we try to classify different groups of arrhythmia using HRV signal processing especially the nonlinear processing. Our main aim is to... 

Medical images contain information about vital organic tissues inside of the human body and are widely used for diagnoses of diseases or for surgical purposes. Image Reconstruction is essential for medical imaging for medical systems like suppression of noise or de-blurring from projections in order to have images with better quality and contrast. Due to the vital role of image reconstruction in medical sciences the corresponding algorithms with better efficiency and higher speed is preferable. Most algorithms in the field of image reconstruction are operated in frequency domain such as the filtered back projection which is a popular algorithm for the reconstruction of the medical images. In... 

A Wireless Sensor Network is one of the attended research context that is used to meet different requirements of a wide range of applications. One of the usages of WSNs is in Animal Tracking. Many Animal Tracking methods have weaknesses that can be enhanced. By considering WSN properties and many different usages of Machine Learning techniques reported in a variety of fields and considering Animal Tracking methods characteristics, WSNs can be improved by applying Machine Learning techniques. The main goal of this thesis is to show that with help of Machine Learning techniques, performance of Animal Tracking by means of Wireless Sensor Networks increases. To fulfill this goal, we first...