Sharif Digital Repository

In Persian language, there are some special uncertainties and complexities regarding the extraction of phonemes due to its flexible structure. In this work, we try to solve two problems caused by this issue, homographs disambiguation and Ezafe recognition in Persian text to speech systems.
In this work, two methods are presented for solving the two problems. The first one is a pattern recognition method based on Aho-Corasick algorithm that has the best performance according to the execution time. The second method is a hidden Markov model tagger based on Viterbi algorithm that uses bigram and trigram statistics. These methods are run on 10 million word corpus and the results are compared... 

Liquefaction of gases is one of the applications of cryogenic science. Among the gases, Helium has the lowest boiling point, which at a pressure of 1atm is approximately 4.2K. Liquid helium can be used to cool superconductors in transportation equipment, military radars, and medical imaging equipment. For helium liquefaction, various cycles are used; these cycles have different parameters in their structure such as of input mass fraction to expanders, heat exchanger effectiveness, expander arrangement and ... which their analysis for improving the performance of the cycle is important. In this research, the aim is to study 2, 3 and 4 expander cycle with various parameters and structure. For... 

Estimation of demand, for example, for transportation is an important issue for the planning and programming of various systems. Thus, enhancing the predictability power of such models is of high value. Demand stems from choices of individuals, and choice is subject to uncertainty and fuzziness. Uncertainty comes from many factors including incomplete information of decision-maker, and fuzziness comes from many other factors including personal perception regarding the value of the variables affecting choice. This study tries to introduce a new approach in building choice models, in which variables are transformed into another variable by the help of a global wisdom. This wisdom shows the... 

As the crowded cities require public transportation and because of lack of space on the ground, Subway and boring underground tunnels encountered. In this thesis the interaction of boring the line 7 of Tehran metro with the existing station of line 1 of Tehran metro (Molavi station) is studied. By changing the soil specification, The surface settlement is significant so the soil specification is one of the important parameters of the interaction. For comparinf the effect of these parameters, the soil settlement and bending moments is investigated in different parts of station while the lower tunnel is passing beneath it. The 3D Abaqus software is used for modeling this interaction. In... 

Airplanes usually experience minor position change and height loss during cruise flight, but under normal circumstances the aircraft total energy is adequately acceptable to maintain the trajectory and the desired performance without severe oscillations. On the other hand, if the airplane encounters a wind-shear or microburst during take-off or landing phases, it would be a dangerous situation, as the aircraft kinetic and potential energy levels are not as high.
In this research, a model predictive controller is designed and investigated to allow a transport category aircraft to either escape or penetrate the microburst. In this regard, initially a DMC controller is designed for 6-DoF... 

Recently, Needs for construction of rock structures and underground ones such as tunnels, dam foundations, power plants and caverns built to keep oil, gas and nuclear waste has increased dramatically. In order to design, construct and excavate these underground structures safely and economically, full understanding of rock mass properties, suitable tools and practical techniques of drilling are necessary. Because of existing this discontinuities, including joints and layered rock masses and their effects on mechanical behavior of rock mass, it is necessary for the geomechanical profile, shear strength and failure mechanism of rock mass to be accurately indentified. Shear strength criterions... 

Nanopositioning is the technology to control position of the objects with precision of the scale of nanometers. Nowdays, This technology emerged as one of the components of research and production in the micro and nanometer dimensions, helping researches and producers to carry out many state of the art projects. A nanopositioning device, consists of a support to path guidance, an actuator to apply force and motion, a driving circuit for communication with the actuator, a sensor for measuring displacement, a circuit for reading sensor’s data, a controlling algorithm to reach the desired precision, a controlling hardware to enforce controlling logic, a power supply and a graphical user... 

According to the impossible trinity, countries can only enjoy from two of the following choices simultaneously: fixed exchange rate, free capital flow and independent monetary policy. A part of the economics literature has tried to verify the theory empirically. Some of the researches like Klein and Shambugh(2015) has concluded that the trilemma is valid on the occasion of transferring the effect of base countries interest rate changes to other countries. On the other side, a few papers like Ray(2013) has shown that an independent monetary policy can just be obtained by a closed capital flow and a float exchange rate system can not necessarily give central banks the autonomy of monetary... 

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... 

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... 

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... 

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... 

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.... 

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... 

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... 

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... 

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...