|
عنوان مقاله |
نویسنده (ها) |
مربوط به کنفرانس |
چکیده |
|
|
Unseen Unit Generation for Unit Selection-based Concatenative Speech Synthesis |
Majid Namnabat
M. Mehdi Homayounpour
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
The unit selection speech synthesis method is accounted of concatenative speech synthesis methods that it produces
more natural quality speech than other approaches. So developing and improvement of this approach attracts ... مشاهده کامل
The unit selection speech synthesis method is accounted of concatenative speech synthesis methods that it produces
more natural quality speech than other approaches. So developing and improvement of this approach attracts great
attraction to produce more natural output speech. Synthesis unit is one of important factors that have great effect on
output quality of synthesizer systems. Using phones as synthesis unit can cause more natural output, however the
discontinuity at the boundaries of concatenated phonemes can be potentially increased in output speech. In this paper,
we proposed using unseen unit generation idea to eliminate discontinuities at phoneme boundaries when phone
instances are used as synthesis units. In proposed method, existence discontinuities at phoneme boundaries in output
speech are firstly found and then if it possible, one of adjacent phonemes of these boundaries are replaced by a suitable
unseen unit. To synthesizing every unseen unit, left half phone of one existence instance of corpus are merged by right
half phone of other existence instance. Perceptual Evaluations show quality output improvement due to decreasing
discontinuities at boundaries. عدم مشاهده کامل
The unit selection speech synthesis method is accounted of concatenative speech synthesis methods that it produces
more natural quality speech than other approaches. So developing and improvement of this approach attracts ... مشاهده کامل |
خرید مقاله
|
|
An Energy Conservation in Hierarchical Clustering Architecture for Wireless Sensor Network |
M. Hossein Fotouhi Ghazvini
Maryam Vahabi
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
A wireless network consisting of a large number of small sensors with low-power transceivers can be an
effective tool for gathering data in a variety of environments. The data collected by ... مشاهده کامل
A wireless network consisting of a large number of small sensors with low-power transceivers can be an
effective tool for gathering data in a variety of environments. The data collected by each sensor is communicated
through the network to a single processing center that uses all reported data to determine characteristics of the
environment or detect an event. The communication or message passing process must be designed to conserve
the limited energy resources of the sensors. This paper derives an algorithm for minimizing energy consumption
by a hierarchical wireless sensor network in transmitting data from source to sink. We assume a single-hop
multi-level clustered network. The stochastic geometry is used to analytically determine the optimum number of
clusters at each level, to show that a multi-level approach can significantly reduce the required network energy. عدم مشاهده کامل
A wireless network consisting of a large number of small sensors with low-power transceivers can be an
effective tool for gathering data in a variety of environments. The data collected by ... مشاهده کامل |
خرید مقاله
|
|
Local Promotion by Cellular Automata to Improve Genetic Search Strategy |
Behrouz Shahgholi Ghahfarokhi
Mohammad Babaeizade
Amir Hassan Monadjemi
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
In recent years, optimization problems are considered as complex problems which require accurate and fast
search methods. Traditional search methods such as iterative search and evolutionary algorithms are not
efficient since they ... مشاهده کامل
In recent years, optimization problems are considered as complex problems which require accurate and fast
search methods. Traditional search methods such as iterative search and evolutionary algorithms are not
efficient since they are not complete and their convergence rate is slow. A lot of efforts have been carried out to
improve the performance of genetic algorithms as a special class of evolutionary algorithms. The most
considerable ones are related to using the idea of cellular automata due to its nature of local operation. However,
a genetic cellular automaton considers the relationship between chromosomes, but sometimes is not efficient
enough due to the early convergence problem. Also, the tradeoff between fast convergence and optimum
exploration is unavoidable. In this paper, we propose a new genetic-based search method using cellular
automata. In this method, in contrast to the traditional genetic cellular automata, the transition rule of cellular
automata is utilized to promote the individuals before genetic operations have been accomplished globally. The
experimental results have shown better convergence rate and also exploration accuracy compared to the
traditional search methods. عدم مشاهده کامل
In recent years, optimization problems are considered as complex problems which require accurate and fast
search methods. Traditional search methods such as iterative search and evolutionary algorithms are not
efficient since they ... مشاهده کامل |
خرید مقاله
|
|
A Comparison of Plane Sweep Delaunay Triangulation Algorithms Ahmad Biniaz1, Gholamhossein Dastghaibyfard2 |
Ahmad Biniaz
Gholamhossein Dastghaibyfard
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
This paper presents a survey as well as a new sweep-circle algorithm, on plane sweep algorithms for computing
the Delaunay triangulation. The algorithms examined are: Fortune’s sweep-line algorithm, Zalik’s sweep-line
algorithm, and ... مشاهده کامل
This paper presents a survey as well as a new sweep-circle algorithm, on plane sweep algorithms for computing
the Delaunay triangulation. The algorithms examined are: Fortune’s sweep-line algorithm, Zalik’s sweep-line
algorithm, and a sweep-circle algorithm proposed by Adam, Kauffmann, Schmitt, and Spehner.
We test implementations of these algorithms on a number of uniform and none-uniform distributed sites. We
also analyze the major high-level primitives that algorithms use and do an experimental analysis of how often
implementations of these algorithms perform each operation. عدم مشاهده کامل
This paper presents a survey as well as a new sweep-circle algorithm, on plane sweep algorithms for computing
the Delaunay triangulation. The algorithms examined are: Fortune’s sweep-line algorithm, Zalik’s sweep-line
algorithm, and ... مشاهده کامل |
خرید مقاله
|
|
Conceptual Design of an e-Research Environment |
Seyed Ebrahim Abtahi
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
In this paper a conceptual design for development of an e-research environment is proposed. In this
environment services are proposed by several components such as virtual library ,data mining tool ,
frame ... مشاهده کامل
In this paper a conceptual design for development of an e-research environment is proposed. In this
environment services are proposed by several components such as virtual library ,data mining tool ,
frame based causal model , Hyper value & reference and report generator and a computer aided model
analysis component. Prototype of this environment has been used to implement two different applied
researches. عدم مشاهده کامل
In this paper a conceptual design for development of an e-research environment is proposed. In this
environment services are proposed by several components such as virtual library ,data mining tool ,
frame ... مشاهده کامل |
خرید مقاله
|
|
Conceptual Design and Feasibility Study for Implementation of and Intelligent help desk over Iran Trade Point |
Seyed Ebrahim Abtahi
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
In this article an intelligent ETO(Electronic Trade Opportunity) help desk is conceptually designed to be
implemented as an e-service on IRAN Trade Point. Users including exporters and importers may access to
information ... مشاهده کامل
In this article an intelligent ETO(Electronic Trade Opportunity) help desk is conceptually designed to be
implemented as an e-service on IRAN Trade Point. Users including exporters and importers may access to
information services , distributed ETO , latest export and import workflow and updated regulations .These
services will be accessible for stakeholders and partners of trade system over Internet. Feasibility study
of implementation alternatives also has been carried out by a score model. عدم مشاهده کامل
In this article an intelligent ETO(Electronic Trade Opportunity) help desk is conceptually designed to be
implemented as an e-service on IRAN Trade Point. Users including exporters and importers may access to
information ... مشاهده کامل |
خرید مقاله
|
|
Formal Development of Two Player Games: A Constructive Approach |
Hassan Haghighi
Seyyed Hassan Mirian-Hosseinabadi
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
In a two player game, the choices of our player can be modeled by angelic nondeterminism and those of our
opponent by demonic nondeterminism. In this paper, we introduce some notations ... مشاهده کامل
In a two player game, the choices of our player can be modeled by angelic nondeterminism and those of our
opponent by demonic nondeterminism. In this paper, we introduce some notations and semantics to Martin-
Löf's theory of types which facilitate the use of angelic and demonic interpretations of nondeterminism in type
theoretical specifications. Using the proposed, nondeterministic constructs, we can formally specify two player
games and derive them from correctness proofs of their formal specifications. عدم مشاهده کامل
In a two player game, the choices of our player can be modeled by angelic nondeterminism and those of our
opponent by demonic nondeterminism. In this paper, we introduce some notations ... مشاهده کامل |
خرید مقاله
|
|
Language Identification from Text Using HMMs |
Oktie Hassanzadeh
Ehsan Zamiri
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
Language identification from text has received less attention than identification from other forms of input.
This is due to the fact that it is considered an easy problem. Several techniques exist ... مشاهده کامل
Language identification from text has received less attention than identification from other forms of input.
This is due to the fact that it is considered an easy problem. Several techniques exist and it is possible to gain
perfect accuracy in identifying the language of the text in some methods. Nevertheless, there has been very few
works on the accuracy and performance of different techniques with limited input, i.e., accurate detection of the
language with less input length and identification of the language of a short sentence or a single word.
In this paper, we present a method based on Hidden Markov Models (HMMs) for language identification
from text. We use the power of HMMs for detecting language of character strings and show the benefits of using
this model over a simple model. We will show how an extremely simple realization of this model outperforms
simple models in accurately identifying languages of short input strings. عدم مشاهده کامل
Language identification from text has received less attention than identification from other forms of input.
This is due to the fact that it is considered an easy problem. Several techniques exist ... مشاهده کامل |
خرید مقاله
|
|
Technical Solutions for Soccer Simulation 3D |
M. Reza Zakeri Nasab
Mehdi Salmani Jelodar
Mohsen Izadi
Hamide Vosoughpour Yazdchi
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
This paper provides technical solutions for two problems selected from Soccer Simulation 3D domain. The agent
movement equation problem and the localization problem are selected from this domain and investigated using ... مشاهده کامل
This paper provides technical solutions for two problems selected from Soccer Simulation 3D domain. The agent
movement equation problem and the localization problem are selected from this domain and investigated using several
machine learning methods, including neural networks, evolutionary learning and statistical learning. Results show the
remarkable advantage of reinforcing ordinary multi-layer perceptron neural networks with evolutionary algorithms.
Also they confirm the superior performance of support vector machines for regression tasks when the underlying
system is neither dynamic nor chaotic. عدم مشاهده کامل
This paper provides technical solutions for two problems selected from Soccer Simulation 3D domain. The agent
movement equation problem and the localization problem are selected from this domain and investigated using ... مشاهده کامل |
خرید مقاله
|
|
A Distributed approach for Coordination Between Traffic Lights Based on NN_Qlearning |
Shahab Aldin Shamshirband
|
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران |
The single traffic signal control agent improves its control ability with the NNQ-learning method.
This paper proposes a Neural_Network_Q_learning (NNQL) approach with fuzzy reward
designed for online learning of traffic lights behaviors ... مشاهده کامل
The single traffic signal control agent improves its control ability with the NNQ-learning method.
This paper proposes a Neural_Network_Q_learning (NNQL) approach with fuzzy reward
designed for online learning of traffic lights behaviors .The Q-function table becomes too large
for the required state/action resolution. In these cases, tabular Q-learning needs a very long
learning time and memory requirements which makes the implementation of the algorithm in
real-time control architecture impractical. To solve the problem of coordination between three
TSCAs (Traffic Signal Control Agents) we used game theory. To test the efficiency of the
coordination mechanism, a prototype traffic simulator was programmed in visual C++. Results
using cooperative traffic agents are compared to results of control simulations where noncooperative
agents were deployed. The result indicates that the new coordination method
proposed in this paper is effective. عدم مشاهده کامل
The single traffic signal control agent improves its control ability with the NNQ-learning method.
This paper proposes a Neural_Network_Q_learning (NNQL) approach with fuzzy reward
designed for online learning of traffic lights behaviors ... مشاهده کامل |
خرید مقاله
|
.gif){kind=icon}
