Sharif Digital Repository

Various applications of speech processing systems are gaining more and more attention. Performances of these systems are dramatically affected in presence of background noise. Attempts toward improving quality of degraded speech have emerged into filed of speech enhancement which is one of the interesting topics in speech processing domain. In this thesis various single channel speech enhancement methods are studied briefly. Statistical methods as one of the most successful methods are studied more deeply. These methods are divided into two categories of short-term modeling of speech and long-term modeling. The aim of this thesis is to improve the performance of long-term methods of... 

Nowadays there are various means in the field of orbital mechanics used in different levels and their accuracy depends on the theory and complexity of the governing equations used in their development. Most of them just simulate the motion of an orbiting satellite while there exist some commercial products able to provide the user with the orbital performance specifications and almost none of them have a module to design an orbit, based on a required performance such as specific coverage / ground track, shadow/light duration, etc .... Although satisfying performance requirements and a set of orbital elements simultaneously only seems to be possible for some particular orbits, there is an... 

The present study aims at determining the elastic fields of ultra-small flaws and defects. These defects are often introduced undesirably in elastic solids during fabrication and their sizes are normally in the order of couple of nano-meters. In this work, the elastic fields around a circular nano-void subjected to a uniform farfield uniaxial tension, also the elastic fields of a nano-sized mode I crack under remote uniform loading are studied. In this paper the strain gradient theory developed by Mindlin and co-workers in 1960s is employed. According to this theory, the strain energy density assumes the form of a positive-definite function of the strain components and their first gradient.... 

One of the most important parts of vehicles and most of mechanical machines is power transmission system, especially the Gearbox used in them.In order to optimize the use of energy, especially fossil fuel, researchers are looking for new mechanisms to refine the operation of vehicles and other machines.One of the mechanisms which absorbed researcher’s attention during recent years is the Continuously Variable Transmission. By using these gearboxes which are replaced with older samples, we can have the continuous range of aspect ratio between two constant values. This important property causes the decrease of the use of fuel.In recent decades many manufacturers have used different kinds of... 

There are different classes of event-driven softwares. These softwares include Graphical user interface, web application or embedded software. In these kinds of softwares, each user's action while using application is known as "event". The application responds to the action through changing behaviour and then waiting for another event. Testing software is the best way for checking the quality assurance of event-driven softwares. However, there are some problems as cause of creating lots of event sequences in testing these kinds of softwares. Therefore, many solutions are introduced for these problems. The goal of this report, is presenting new testing procedure for event-driven web... 

After discovery of superconductivity in 1911 people try to find superconductors with higher Tc. High Tc superconductivity in cuprates and iron based superconductors was discovered in 1986 and 2008 respectively. However, there is not any unit theory for high Tc superconductivity in cuprates or iron based superconductors. Study of electronic and phonon structures of high Tc superconductor compounds can lead to find theory of high Tc superconductivity.
In this dissertation electronic structure of Ba1-xKxFe2As2, which belongs to class of 122 of iron based superconductor, under potassium doping x=0,0.5,1 has been studied. To this end ab-initio method and Density functional theory have been... 

Flight control system (FCS) design, analysis and modeling has an important role in aircraft design and development process. However, FCS analysis and studies are rarely focused at university levels and its know-how and technical issues are almost proprietary to various aircraft industries. One of the key goals of this thesis is to express, introduce and implement the processes that need to be followed for a sample longitudinal reversible FCS design (RFCS), where the modelling aspects are described for an existing aircraft. The latter is achieved using existing drawings, system and aerodynamic data of an existing aircraft utilizing commercial tools such as CATIA for initial design and ADAMS... 

The discovery of Iron-based superconductors with maximum transition temperature of 56 Kelvin and High critical magnetic field of the order of 50T at temperature 20K has created evolution in different fields of superconductivity including practical issues. BaFe2As2 family is one of the most important compounds of Iron-based superconductors and with different doping elements for instanse elements of the first column like Potassium inters superconducting state with critical temperature of 36K.
The purpose of this thesis is to localize the technology of making this compound in Iran which no project has been done in this field in the country before. In this thesis manufacturing, Optimization... 

Language model is one of the most important parsts of an automated speech recognition system whiche incorporates the knowledge of Natural Language to the system to improve its accuracy. Conventionally used language model in recognition systems is ngram which usually is extracted from a large corpus using related frequency method. ngram model approximates the probability of a word sequence by multiplying its ngram probabilities and thus does not take into account the long distance dependencies. So, syntactic language models could be of interest. In this research after probing different syntactic language models, a mehtod for re-estimating ngram model, introduced by Stolcke in 1994, was... 

The human speech conveys much information such as semantic contents, emotion and even speaker identity. Our goal in this thesis is the task of text-independent speaker identification (SI) in large population applications. Identification (test) time has become one of the most important issues in recent real time systems. Identification time depends on the cost of likelihood computation between test features and registered speaker models. For real time application of SI, system must identify an unknown speaker quickly. Hence the conventional SI methods cannot be used. The main goal in this thesis is to propose several methods that reduced identification time without any loss of identification... 

Measuring emotions of music is one of the methods to determine music content. Music emotion detection is applicable in music retrieval, recognition of music genre and also music data management softwares. Music emotion is considered in different sciences such as physiology, psychology, musicology and engineering. First, we collected a database of different types of music with various emotions. These data have been labeled according to their emotions. In this project, four emotions (Angry, happy, relax and sad) have been used as labels based on Thayer’s two dimension emotion model. There are two basic steps for music emotion recognition similar to other recognition systems: Feature extraction... 

Applying spoken dialogue systems (SDS's) is growing in the real life more rapidly because of the advances in the design and management of these systems. The traditional touch tone computer telephony systems are being substituted by the SDS's. In a typical SDS, the user speaks naturally to the system through a phone line and the system provides the required information or performs the required action. Banking and ticket reservation are typical examples of the prevalent SDS's. A spoken dialogue system has four units: automatic speech recognition (ASR), natural language understanding (NLU), dialogue management (DM), and spoken language generation (SLG). In this work, the first spoken dialogue... 

The utilizing language model is one of the most effective methods for improving speech recognition performance. For speech recognition applications, several types of language models have been proposed for speech recognition applications that try to model some parts of language information, such as n-gram models, syntactic models, and semantic models. Although n-gram, syntactic and semantic models are able to model different structures that exist in natural language, they each only capture specific linguistic phenomena. None of them can simultaneously take into account all of language phenomena in a unified probabilistic framework. Recently, a number of semantic models called "latent topic... 

Signle-channel speech enhancement using hidden Markov model (HMM) based on minimum mean square error (MMSE) estimator is focused on and an HMM-based speech enhancement in Mel-frequency domain is proposed. The MMSE estimator results in a weighted sum filtering of the noisy signal in which accurate estimation of the filter values and filter weights comprise the main challenges. The cepstral domain modeling for speech enhancement is motivated by accurate filter selection in this domain. In the propsed framework, Mel-frequency spectral (MFS) and Mel-frequency cepstral (MFC) features are studied and experimented. In addition to the spectrum estimator, magnitude spectrum, log-magnitude spectrum... 

Scattered and little research in the field of Persian speech synthesis systems has been performed during the last ten years. Comprehensive framework that properly implements and adapts statistical speech synthesis methods for Persian has not been conducted yet. In this thesis, recent statistical parametric speech synthesis methods including CLUSTERGEN, traditional HMM-based speech synthesis and its STRAIGHT version, are implemented and adapted for Persian language. CCR test is carried out to compare these methods with each other and with unit selection method. Listeners Score samples based on CMOS. The methods were ranked by averaging the CCR scores. The results show that STRAIGHT-based... 

Spoken language understanding unit is one of the most important parts of a spoken dialogue system. The input of this system is the output of speech recognition unit. The main function of this unit is to extract the semantic information from the input utterances. There are two main types of approaches to do this task: rule-based approaches, and data-driven approaches. Today data-driven approaches are of more interest because they are more flexible and robust compared to the rule-based approaches. The main drawback of these methods is that they need a large amount of fully annotated or in some cases Treebank data. Preparing such data is time consuming and expensive. The goal of this thesis is... 

Semantic classification of words based on unsupervised learning methods is a challenging issue in computational lexical semantics. The goal of this field of study is to recognize the words that are in the same semantic classes; i.e., can have the same set of arguments. Among all word categories, verb is known as one the most important and is assumed as the central part of the sentence in certain linguistic theories such as case grammar and dependency grammar. Based on Levin’s idea, diathesis alternations and the similarity between these alternations are the clues for the semantic classification of verbs. This idea is verified in languages such as English and German with promising results.... 

Automatic speech recognition performance degrades significantly when speech is affected by environmental noise. Nowadays, the major challenge is to achieve good robustness in adverse noisy conditions so that automatic speech recognizers can be used in real situations. Spectral subtraction (SS) is a well-known and effective approach; it was originally designed for improving the quality of speech signal judged by human listeners. SS techniques usually improve the quality and intelligibility of speech signal while speech recognition systems need compensation techniques to reduce mismatch between noisy speech features and clean trained acoustic model. Nevertheless, correlation can be expected... 

Recently various speaker adaptation methods in HMM-based speech synthesis are proposed. The importance of adaptation techniques is that we can design a system in which speech is generated with high quality and target speaker characteristics through limited adaptation data sets.
In this research, we focus on adaptation based on clustering and develop a new and novel method using eigenvoices in order to adapt a new speaker. We employ this approach for the first time in HSMM-based speech synthesis systems and its goal is to reduce the parameters and adaptation data of the system. In our proposed method, first some speaker dependent models are trained. For each model we combine the...