Inter-speaker variability, one of the problems faced in speech recognition system, has caused the performance degradation in recognizing varied speech spoken by different speakers. Vocal Tract Length Normalization (V...
详细信息
Inter-speaker variability, one of the problems faced in speech recognition system, has caused the performance degradation in recognizing varied speech spoken by different speakers. Vocal Tract Length Normalization (VTLN) method is known to improve the recognition performances by compensating the speech signal using specific warping factor. Experiments are conducted using TIMIT speech corpus and Hidden Markov Model Toolkit (HTK) together with the implementation of VTLN method in order to show improvement in speaker independent phoneme recognition. The results show better recognition performance using Bigram Language Model compared to Unigram Language Model, with Phoneme Error Rate (PER) 28.8% as the best recognition performance for Bigram and PER 38.09% for Unigram. The best warp factor used for normalization in this experiment is 1.40.
Nowadays, the concept of urban and urbanism in regards to problems such as increasing population, multiplicity in number of cities, air and noise pollution and traffic jams evolved in deep variation and changes. Recen...
详细信息
Nowadays, the concept of urban and urbanism in regards to problems such as increasing population, multiplicity in number of cities, air and noise pollution and traffic jams evolved in deep variation and changes. Recently, with this approach we will face the question of what is sustainable to the city and regarding goals of sustainable development, how we could implement the vision based on this theory in modern urbanism. It is obvious that rapid changes in physical and economical development joint with social changes will have an influence on live dynamic of cities. Information technology is known as one of the most important elements in changes and development of the current world and consequences from it will have a direct impact on people. These changes will carry words such as: Electronic commerce, Electronic Banking, Electronic city and even electronic government. It's been many years that Electronic development is practically used in many countries yielding large capital returns and saving significant resources and capacities for those countries. Electronic city as one of the emerging concept which is born with the development of Information technology, in theoretical and practical field, it can cause innovation and creation by using social and economical capitals. Also it could be a model to achieve sustainable development goals and solve many problems of New Urbanism. Noticeably, with regards to this fact, more than half the world's population live in urban areas and concept of the city is in the center of major challenges and problems such as energy control, resource consuming and change in cities infrastructure, "sustainable city" and its creation will not be possible unless we again have an approach to city development in the form of sustainability concept. Finally, Goal of this paper is to introduce overall aim of sustainable development and consider the role and necessity of electronic city and required infrastructure in order to make it practical.
Subdivision surfaces were applied to the entire meshes in order to produce smooth surfaces refinement from coarse mesh. Several schemes had been introduced in this area to provide a set of rules to converge smooth sur...
详细信息
Subdivision surfaces were applied to the entire meshes in order to produce smooth surfaces refinement from coarse mesh. Several schemes had been introduced in this area to provide a set of rules to converge smooth surfaces. However, to compute and render all the vertices are really inconvenient in terms of memory consumption and runtime during the subdivision process. It will lead to a heavy computational load especially at a higher level of subdivision. Adaptive subdivision is a method that subdivides only at certain areas of the meshes while the rest were maintained less polygons. Although adaptive subdivision occurs at the selected areas, the quality of produced surfaces which is their smoothness can be preserved similar as well as regular subdivision. Nevertheless, adaptive subdivision process burdened from two causes;calculations need to be done to define areas that are required to be subdivided and to remove cracks created from the subdivision depth difference between the selected and unselected areas. Unfortunately, the result of adaptive subdivision when it reaches to the higher level of subdivision, it still brings the problem with memory consumption. This research brings to iterative process of adaptive subdivision to improve the previous adaptive method that will reduce memory consumption applied on triangular mesh. The result of this iterative process was acceptable better in memory and appearance in order to produce fewer polygons while it preserves smooth surfaces.
Testing is crucial in software development. Continuous researches being done to discover effective approaches in testing that capable to detect faults despite of reducing cost. Previous work in State-Sensitivity Parti...
详细信息
Testing is crucial in software development. Continuous researches being done to discover effective approaches in testing that capable to detect faults despite of reducing cost. Previous work in State-Sensitivity Partitioning (SSP) technique, which based on all-transition coverage criterion, has been introduced to avoid exhaustively testing the entire data states of a module by partitioning it based on state's sensitivity towards events, conditions and action. The test data for that particular module testing is in form of event sequences (or test sequence) and sets of test sequences in test cases will perform SSP test suite. The problem occurs in SSP test suite is data state redundancy that leads towards suite growth. This paper aims to discuss an initial step of our ongoing research in enhancing prior SSP test suite. Our work will try to find out the best way in removing redundant data state in order to minimize the suite size but yet capable to detect faults introduced by five selective mutation operators effectively as the original suite.
Cost functions that involve complex simulations are becoming more common for engineering design *** cost functions are very CPU intensive and their optimization by exact algorithms need complex *** are some approaches...
详细信息
Cost functions that involve complex simulations are becoming more common for engineering design *** cost functions are very CPU intensive and their optimization by exact algorithms need complex *** are some approaches in the literature to decrease the overall computational *** needs some experience to know the suitable evaluation algorithm for a defined ***,finding the optimum point in a short search time needs an intelligent search *** this article,a new solution approach is proposed to achieve near global optimal point in a reasonable time for complex cost *** proposed approach has been implemented for some test *** results show that this approach has better performance comparing to other existing solution algorithms such as Genetic Algorithm,Differential Evolution,Evolution Strategy,and Particle Swarm Optimization.
We have proposed the concept of a presence sharing system Ghatcha [GHost Avatar on a Telework CHAir] in which the users' embodiment is not indicated by the avatars but by the chairs that suggest the presence of av...
详细信息
Since the reusing and arranging of available Web services have been raised, the amount of infrastructure strategies based on Service Oriented architecture (SOA) is increasing. Hence, a rich Semantic Web service descri...
详细信息
Since the reusing and arranging of available Web services have been raised, the amount of infrastructure strategies based on Service Oriented architecture (SOA) is increasing. Hence, a rich Semantic Web service description is needed to achieve an automated Web service discovery, composition and invocation. On the other hand, the acceptance of Semantic Web service is still decelerating because of its language complexity and lack of knowledge in the field of knowledge engineering and knowledge representation among developers. Due to the proper assessment of model-driven approaches that are used to develop Semantic Web services, it is significant to have an appropriate categorization of these approaches. Thus, the key goal of this paper is to classify several model-driven approaches for developing Semantic Web services. Based on this study, there are three main categories namely software methodology, meta-model, and UML formalist based approaches.
The successful of a construction industry project depends on contractor evaluation and selection. Further, human judgment and unknown evaluation risk make evaluation and selection increasingly complex. Such situations...
详细信息
The successful of a construction industry project depends on contractor evaluation and selection. Further, human judgment and unknown evaluation risk make evaluation and selection increasingly complex. Such situations show that a contractor selection is influenced by multiple attributes that often have the hybrid uncertainty of fuzziness and probability. The objective of this study is therefore to propose a fuzzy random variable based multi-attribute decision scheme that enables us to solve such problems within the bounds of hybrid uncertainty by using a fuzzy random regression model. The proposed model is explained in examples and its usefulness is clarified. This decision model is facilitated in its use by evaluating alternatives and enables us to indicate the optimum choice in the presence of hybrid uncertainty.
Lack of hearing ability hinders deaf children from mastering grammar in language studies. Unfortunately, such software targeting Malay language is limited. This paper attempts to generate new approach in handling such...
详细信息
Lack of hearing ability hinders deaf children from mastering grammar in language studies. Unfortunately, such software targeting Malay language is limited. This paper attempts to generate new approach in handling such software. These include detection of defects when switching into local languages, date format and accommodating the local laws. The acceptance of international software for local use goes beyond just these aspects. For this purpose, software that supports the multi-languages is evaluated. The main research question of this paper: The lack of cultural dimensions in localisation testing of assistive technology decreases the effectiveness of localisation testing of the localised software. On the account of cultural dimensions, Hofstede's Cultural Dimensions will be experimented to study which cultural dimensions are most suited for such software. From our empirical results, the failure rate of the testing is higher compared to incorporating culture dimensions.
High packet network have become an essential in modern multimedia communication. Shared buffer is commonly used to utilize the buffer in the switch. In this paper, we analyse the performance of shared buffer with diff...
详细信息
ISBN:
(纸本)9781457703898
High packet network have become an essential in modern multimedia communication. Shared buffer is commonly used to utilize the buffer in the switch. In this paper, we analyse the performance of shared buffer with different memory sizes. The architecture of the multi-class shared buffer is developed for 16×16 ports switch that is targeted in Xilinx FPGA. The performance of the multi-class shared buffer switch is analysed in term of throughput and mean delay. Based on the simulation with different memory sizes, it is observed that the optimum selection of memory size under uniform traffic depends on the maximum traffic load of the switch.
暂无评论