Loading...
Search for:
khorram--s
0.117 seconds
Total 10340 records
HMM-based persian speech synthesis using limited adaptation data
, Article International Conference on Signal Processing Proceedings, ICSP ; Volume 1 , 2012 , Pages 585-589 ; 9781467321945 (ISBN) ; Sameti, H ; Khorram, S ; Sharif University of Technology
2012
Abstract
Speech synthesis systems provided for the Persian language so far need various large-scale speech corpora to synthesize several target speakers' voice. Accordingly, synthesizing speech with a small amount of data seems to be essential in Persian. Taking advantage of a speaker adaptation in the speech synthesis systems makes it possible to generate speech with remarkable quality when the data of the speaker are limited. Here we conducted this method for the first time in Persian. This paper describes speaker adaptation based on Hidden Markov Models (HMMs) in Persian speech synthesis system for FARsi Speech DATabase (FARSDAT). In this regard, we prepared the whole FARSDAT, then for...
Implementation and evaluation of statistical parametric speech synthesis methods for the Persian language
, Article IEEE International Workshop on Machine Learning for Signal Processing, 18 September 2011 through 21 September 2011 ; September , 2011 , Page(s): 1 - 6 ; 9781457716232 (ISBN) ; Sameti, H ; Khorram, S ; Sharif University of Technology
2011
Abstract
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 paper, 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...
Soft context clustering for F0 modeling in HMM-based speech synthesis
, Article Eurasip Journal on Advances in Signal Processing ; Volume 2015, Issue 1 , January , 2015 ; 16876172 (ISSN) ; Sameti, H ; King, S ; Sharif University of Technology
Springer International Publishing
2015
Abstract
This paper proposes the use of a new binary decision tree, which we call a soft decision tree, to improve generalization performance compared to the conventional ‘hard’ decision tree method that is used to cluster context-dependent model parameters in statistical parametric speech synthesis. We apply the method to improve the modeling of fundamental frequency, which is an important factor in synthesizing natural-sounding high-quality speech. Conventionally, hard decision tree-clustered hidden Markov models (HMMs) are used, in which each model parameter is assigned to a single leaf node. However, this ‘divide-and-conquer’ approach leads to data sparsity, with the consequence that it suffers...
Markov properties of electrical discharge current fluctuations in plasma
, Article Journal of Statistical Physics ; Volume 143, Issue 1 , 2011 , Pages 148-167 ; 00224715 (ISSN) ; Movahed, M. S ; Khorram, S ; Rahimi Tabar, M. R ; Sharif University of Technology
2011
Abstract
Using the Markovian method, we study the stochastic nature of electrical discharge current fluctuations in the Helium plasma. Sinusoidal trends are extracted from the data set by the Fourier-Detrended Fluctuation analysis and consequently cleaned data is retrieved. We determine the Markov time scale of the detrended data set by using likelihood analysis. We also estimate the Kramers-Moyal's coefficients of the discharge current fluctuations and derive the corresponding Fokker-Planck equation. In addition, the obtained Langevin equation enables us to reconstruct discharge time series with similar statistical properties compared with the observed in the experiment. We also provide an exact...
Modeling and simulation of oil well stimulation by high power ultrasonic irradiation
, Article Acta Acustica united with Acustica ; Volume 103, Issue 3 , 2017 , Pages 411-420 ; 16101928 (ISSN) ; Ahmad Ramazani, S. A ; Jamshidi, S ; Moghaddam, A. K ; Sharif University of Technology
S. Hirzel Verlag GmbH
2017
Abstract
Ultrasonic waves have been extensively used in many industrial applications including clean devices, pipes and vessels. A clear extension of this usage is the removal of wellbore contaminants by exposing it to high-power ultrasonic waves. In this paper, a mathematical model for ultrasonic propagation through the porous medium around the wellbore is presented. The equations of wave propagation are written in a cylindrical coordinate according to Biot theory and the induced stress in the rock are calculated at each point using finite difference approach Comparison of imposed local stresses with adhesion forces between scales and rock, the properties of ultrasonic transducer, such as frequency...
Fractal properties of plasma discharge current fluctuations
, Article 36th EPS Conference on Plasma Physics 2009, EPS 2009 - Europhysics Conference Abstracts, 29 June 2009 through 3 July 2009, Sofia ; Volume 33 E1 , 2009 , Pages 645-648 ; 9781622763368 (ISBN) ; Movahed, M. S ; Rahimi Tabar, M. R ; Sobhanian, S ; Khorram, S ; Sharif University of Technology
2009
Abstract
We use multifractal detrended fluctuation analysis (MF-DFA) to study the electrical discharge current fluctuations in plasma and show that it has multifractal properties and behaves as a weak anti-correlated process. Comparison of the MF-DFA results for the original series with those for the shuffled and surrogate series shows that correlation of the fluctuations is responsible for the multifractal nature of the electrical discharge current
An automatic prosodic event detector using MSD HMMs for Persian language
, Article Communications in Computer and Information Science ; Vol. 427, issue , 2014 , p. 234-240 ; Shams, B ; Sameti, H ; Khorram, S ; Sharif University of Technology
2014
Abstract
Automatic detection of prosodic events in speech such as detecting the boundaries of Accentual Phrases (APs) and Intonational Phrases (IPs) has been an attractive subject in recent years for speech technologists and linguists. Prosodic events are important for spoken language applications such as speech recognition and translation. Also in order to generate natural speech in text to speech synthesizers, the corpus should be tagged with prosodic events. In this paper, we introduce and implement a prosody recognition system that could automatically label prosodic events and their boundaries at the syllable level in Persian language using a Multi-Space Probability Distribution Hidden Markov...
Optimal transmission switching as a remedial action to enhance power system reliability
, Article 2016 Smart Grids Conference, SGC 2016, 20 December 2016 through 21 December 2016 ; 2017 , Pages 7-12 ; 9781509049882 (ISBN) ; Fotuhi Firuzabad, M ; Safdarian, A ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2017
Abstract
Increasing redundant paths in transmission grids has always been thought to be a tool to enhance service reliability. However, network equations by intertwining power flows through redundant paths impose more limits on systems with more redundancy. Accordingly, autonomous removing of a few lines may relief capacity limit violations in some contingency events thereby enhancing service reliability. This paper aims to study impacts of manual removing of transmission lines on composite system reliability. For doing so, the existing model is extended to consider optimal transmission switching (OTS) as a remedial action. The model minimizes total damage cost imposed by load curtailments. The...
Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis
, Article Eurasip Journal on Audio, Speech, and Music Processing ; Vol. 2014, Issue. 1 , 2014 ; ISSN: 1687-4714 ; Sameti, H ; Bahmaninezhad, F ; King, S ; Drugman, T ; Sharif University of Technology
2014
Abstract
Decision tree-clustered context-dependent hidden semi-Markov models (HSMMs) are typically used in statistical parametric speech synthesis to represent probability densities of acoustic features given contextual factors. This paper addresses three major limitations of this decision tree-based structure: (i) The decision tree structure lacks adequate context generalization. (ii) It is unable to express complex context dependencies. (iii) Parameters generated from this structure represent sudden transitions between adjacent states. In order to alleviate the above limitations, many former papers applied multiple decision trees with an additive assumption over those trees. Similarly, the current...
Fractal analysis of discharge current fluctuations
, Article Journal of Statistical Mechanics: Theory and Experiment ; Volume 2009, Issue 3 , 2009 ; 17425468 (ISSN) ; Sadegh Movahed, M ; Khorram, S ; Sobhanian, S ; Rahimi Tabar, M. R ; Sharif University of Technology
Institute of Physics Publishing
2009
Abstract
We use multifractal detrended fluctuation analysis (MF-DFA) to study the electrical discharge current fluctuations in plasma and show that it has multifractal properties and behaves as a weak anti-correlated process. Comparison of the MF-DFA results for the original series with those for the shuffled and surrogate series shows that correlation of the fluctuations is responsible for the multifractal nature of the electrical discharge current. © 2009 IOP Publishing Ltd. and SISSA
Improving Speech Signal Models for Statistical Parametric Speech Synthesis
, Ph.D. Dissertation Sharif University of Technology ; Sameti, Hossein (Supervisor)
Abstract
Statistical parametric speech synthesis (SPSS) has dominated speech synthesis research area over the last decade, due to its remarkable advantages such as high intelligibility and flexibility. Decision tree-clustered context-dependent hidden semi-Markov models are typically used in SPSS to represent probability densities of acoustic features given contextual factors. This research addresses four major limitations of this decision tree-based structure: (a) The decision tree structure lacks adequate context generalization; (b) It is unable to express complex context dependencies; (c) Parameters generated from this structure represent sudden transitions between adjacent states; (e) This...
Model-Driven Methodology for Developing Serious Games in the Context of Business Processes
, M.Sc. Thesis Sharif University of Technology ; Ramsin, Raman (Supervisor)
Abstract
Education has become a crucial issue worldwide, and it needs new techniques and technologies to create and raise interest and motivation towards learning. Serious games are gaining acclaim as viable solutions for enhancing educational processes; Serious games are interactive computer applications that use a challenging and amusing context to transfer a practical skill, knowledge or attitude to their users. Organizations and companies need an effective way for teaching their business processes to their employees. There are many business-related serious games. but few of them focus on business processes, most of which are business-specific and no precise approach is used in their development,...
Level crossing analysis of growing surfaces
, Article Journal of Physics A: Mathematical and General ; Volume 36, Issue 10 , 2003 , Pages 2517-2524 ; 03054470 (ISSN) ; Sobhanian, S ; Rahimi Tabar, M. R ; Khorram, S ; Frootan, G. R ; Zahed, H ; Sharif University of Technology
2003
Abstract
We investigate the average frequency of positive slope v α+, crossing the height α = h - h̄ in the surface growing processes. The exact level crossing analysis of the random deposition model and the Kardar-Parisi-Zhang equation in the strong coupling limit before creation of singularities is given
Optimal transmission switching as a remedial action to enhance composite system reliability
, Article 2015 Smart Grid Conference, SGC 2015, 23 December 2015 through 24 December 2015 ; 2017 , Pages 152-157 ; 9781509003693 (ISBN) ; Abbaspour Tehrani Fard, A ; Fotuhi Firuzabad, M ; Safdarian, A ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2017
Abstract
Increasing redundant paths in transmission grids has always been thought to be a tool to enhance service reliability. However, network equations by intertwining power flows through redundant paths impose more limits on systems with more redundancy. Accordingly, autonomous removing of a few lines may relief capacity limit violations in some contingency events thereby enhancing service reliability. This paper aims to study impacts of manual removing of transmission lines on composite system reliability. For doing so, the existing model is extended to consider optimal transmission switching (OTS) as a remedial action. The model minimizes total damage cost imposed by load curtailments. The...
Speech synthesis based on gaussian conditional random fields
, Article Communications in Computer and Information Science ; Vol. 427, issue , 2014 , p. 183-193 ; Bahmaninezhad, F ; Sameti, H ; Sharif University of Technology
2014
Abstract
Hidden Markov Model (HMM)-based synthesis (HTS) has recently been confirmed to be the most effective method in generating natural speech. However, it lacks adequate context generalization when the training data is limited. As a solution, current study provides a new context-dependent speech modeling framework based on the Gaussian Conditional Random Field (GCRF) theory. By applying this model, an innovative speech synthesis system has been developed which can be viewed as an extension of Context-Dependent Hidden Semi Markov Model (CD-HSMM). A novel Viterbi decoder along with a stochastic gradient ascent algorithm was applied to train model parameters. Also, a fast and efficient parameter...
An optimum MMSE post-filter for Adaptive Noise Cancellation in automobile environment
, Article 2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012 ; 2012 , Pages 431-435 ; 9781467303828 (ISBN) ; Sameti, H ; Veisi, H ; Sharif University of Technology
2012
Abstract
Adaptive Noise Cancellation (ANC) is an effective dual-channel technique for background noise reduction. Due to the presence of uncorrelated noise components at the two inputs in vehicular environments, ANC does not provide sufficient background noise reduction. To alleviate this problem, a complementary linear filter is added to ANC structure. Filter coefficients are determined to make the enhanced signal an MMSE estimation of speech signal. Therefore, the ANC structure is modified to a dual-channel Wiener structure. We prove that this structure is identical to the LMS type ANC which is followed by a Wiener post-filter. A new method is proposed for the noise spectrum estimation in the...
LP-based over-sampled subband adaptive noise canceller for speech enhancement in diffuse noise fields
, Article 2008 9th International Conference on Signal Processing, ICSP 2008, Beijing, 26 October 2008 through 29 October 2008 ; 2008 , Pages 157-161 ; 9781424421794 (ISBN) ; Sameti, H ; Veisi, H ; Sharif University of Technology
2008
Abstract
Adaptive Noise Cancellers (ANCs) do not provide sufficient noise reduction in the diffuse noise fields. In this paper, a new hybrid structure is proposed as a solution to this problem. The proposed system is a combination of two subsystems, an ANC and a new multistage post-filter. The post-filter is based on linear prediction (LP) and attempts to extract speech component by using intermediate ANC signals. The system is implemented on an over-sampled DFT filterbank with different analysis and synthesis prototype filters. The experimental results using various quality measures show that the proposed system is superior to both the subband ANC and subband LP based speech enhancement systems.1 ©...
SeGa4Biz: Model-Driven framework for developing serious games for business processes
, Article 9th International Conference on Model-Driven Engineering and Software Development, MODELSWARD 2021, 8 February 2021 through 10 February 2021 ; 2021 , Pages 139-146 ; 9789897584879 (ISBN) ; Taromirad, M ; Ramsin, R ; Sharif University of Technology
SciTePress
2021
Abstract
Organizations look for effective ways to teach their business processes to their employees. The application of serious games for teaching business processes is getting attraction recently. However, existing works are by large business-specific and few of them aim at teaching business processes in general, besides that the development of such games inherently suffers lack of precise and clear development approaches. This paper presents SeGa4Biz, a model-driven framework for serious game development for teaching business processes. Modeling supports different levels of abstraction and hence, increases user involvement throughout the development. SeGa4Biz particularly provides metamodels for...
Acceleration of the MWDM in Site Specific indoor Propagation Modeling Using Algorithm Optimization and Parallel Computation
, M.Sc. Thesis Sharif University of Technology ; Shishegar, Amir Ahmad (Supervisor)
Abstract
There is an ever rising interest for propagation simulation and communication channel modeling in indoor environments. Thus the demand for the development of proper software to perform these computations has been the motivation for a lot of researches on proper algorithms for these calculations. The most popular one is the ray tracing which is faster than other algorithms and needs only simple calculations. Still, the large number of these calculations needed to achieve proper accuracy does not allow ray tracing to achieve the desired speed in indoor environments. Numbers of methods have been proposed to increase its speed. One of which is the modified wavefront decomposition method which is...
A new lattic LP-based post filter for adaptive noise cancellers in mobile and vehicular applications
, Article Proceedings of the 8th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2008, 16 December 2008 through 19 December 2008, Sarajevo ; 2008 , Pages 407-412 ; 9781424435555 (ISBN) ; Sameti, H ; Veisi, H ; Abutalebi, H. R ; Sharif University of Technology
2008
Abstract
Adaptive Noise Cancellation (ANC) is a well-known technique for background noise reduction in automobile and vehicular environments. The noise fields in automobile and other vehicle interior obey the diffuse noise field model closely. On the other hand, the ANC does not provide sufficient noise reduction in the diffuse noise fields. In this paper, a new multistage post-filter is designed for ANC as a solution to diffuse noise conditions. The designed post-filter is a single channel Linear Prediction (LP) based speech enhancement system. The LP is performed by an adaptive lattice filter and attempts to extract speech components by using intermediate ANC signals. The post-filter has no...