The Experts below are selected from a list of 288 Experts worldwide ranked by ideXlab platform
R.n. Gorgui-naguib - One of the best experts on this subject based on the ideXlab platform.
-
ICNN - A scaly artificial neural network architecture for isolated word recognition using the British Telecommunications English Alphabet database
IEEE International Conference on Neural Networks, 1Co-Authors: M J Creaney, R.n. Gorgui-naguibAbstract:The use of neural networks for the recognition of isolated letters from the English Alphabet is investigated. A scaly architecture neural network model is used and is trained using the error backpropagation algorithm. Two different methods of nonlinear time alignment are used and the performance of the neural network when used with each is compared. The use of different transfer functions within the processing units of the neural network is examined, and several versions of the sigmoid function are compared. The variance of the learning rate in the error backpropagation algorithm is investigated by comparing the performance of the neural network when three different values of learning rate are used. >
-
A scaly artificial neural network for speaker independent isolated word recognition using non-linear time alignment
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94), 1Co-Authors: M J Creaney, R.n. Gorgui-naguibAbstract:The use of neural networks for the recognition of isolated letters from the English Alphabet is investigated. A scaly architecture neural network model is used and is trained using the error backpropagation algorithm. The architecture is varied by changing the number of inputs to the network, the number of hidden units in the network and the performance of each of these networks is compared. The nonlinear time alignment algorithm called trace segmentation is used. The use of different transfer functions within the processing units of the neural network is looked at and several versions of the sigmoid function compared. >
M J Creaney - One of the best experts on this subject based on the ideXlab platform.
-
a scaly artificial neural network architecture for isolated word recognition using the british telecommunications English Alphabet database
IEEE International Conference on Neural Networks, 1993Co-Authors: M J Creaney, R N GorguinaguibAbstract:The use of neural networks for the recognition of isolated letters from the English Alphabet is investigated. A scaly architecture neural network model is used and is trained using the error backpropagation algorithm. Two different methods of nonlinear time alignment are used and the performance of the neural network when used with each is compared. The use of different transfer functions within the processing units of the neural network is examined, and several versions of the sigmoid function are compared. The variance of the learning rate in the error backpropagation algorithm is investigated by comparing the performance of the neural network when three different values of learning rate are used. >
-
ICNN - A scaly artificial neural network architecture for isolated word recognition using the British Telecommunications English Alphabet database
IEEE International Conference on Neural Networks, 1Co-Authors: M J Creaney, R.n. Gorgui-naguibAbstract:The use of neural networks for the recognition of isolated letters from the English Alphabet is investigated. A scaly architecture neural network model is used and is trained using the error backpropagation algorithm. Two different methods of nonlinear time alignment are used and the performance of the neural network when used with each is compared. The use of different transfer functions within the processing units of the neural network is examined, and several versions of the sigmoid function are compared. The variance of the learning rate in the error backpropagation algorithm is investigated by comparing the performance of the neural network when three different values of learning rate are used. >
-
A scaly artificial neural network for speaker independent isolated word recognition using non-linear time alignment
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94), 1Co-Authors: M J Creaney, R.n. Gorgui-naguibAbstract:The use of neural networks for the recognition of isolated letters from the English Alphabet is investigated. A scaly architecture neural network model is used and is trained using the error backpropagation algorithm. The architecture is varied by changing the number of inputs to the network, the number of hidden units in the network and the performance of each of these networks is compared. The nonlinear time alignment algorithm called trace segmentation is used. The use of different transfer functions within the processing units of the neural network is looked at and several versions of the sigmoid function compared. >
A. K. Agarwal - One of the best experts on this subject based on the ideXlab platform.
-
Digit letter substitution test (DLST) as an alternative to digit symbol substitution test (DSST)
Human Psychopharmacology: Clinical and Experimental, 1995Co-Authors: M. V. Natu, A. K. AgarwalAbstract:In the present study, a modification has been suggested in DSST to overcome some of its demerits. In the new test, DLST, the symbols have been substituted by letters from the English Alphabet. The new test seems to be stable, valid and sensitive. It has similar basic structure and sensitivity with added advantage of better understanding by subjects, easy preparation of parallel work sheets and faster evaluation. We propose that the new test may serve as a good alternative to DSST.
Nianshing Chen - One of the best experts on this subject based on the ideXlab platform.
-
gesture based learning for preschooler a case study of teaching English Alphabet and body parts vocabulary
International Conference on Advanced Learning Technologies, 2016Co-Authors: Chianing Hsu, Iling Cheng, Sie Wai Chew, Chunyu Zhu, Pinyang Liu, Nianshing ChenAbstract:English is a world recognized global language. Different methods used in teaching and learning English is widely discussed and researched in the education field. Due to the language's importance, the learning age of English is beginning at a younger age in Taiwan, some even started from toddlers. In our study, we are exploring the effects of preschoolers learning English using a gesture-based system compared to learning English using word cards. The system is designed to enhance and improve the preschooler's learning performance of the language. Our target subjects do not have basic knowledge of the language. The results of the study showed that there are no significant difference between the two learning groups. However, it was found that the participant's age and those having past experience of using gesture-based systems had shown to have significant effect on their learning performance. The limitation and future study of this study is also discussed.
Krist Roginski - One of the best experts on this subject based on the ideXlab platform.
-
English Alphabet recognition with telephone speech
Neural Information Processing Systems, 1991Co-Authors: Mark Fanty, Ronald A Cole, Krist RoginskiAbstract:A recognition system is reported which recognizes names spelled over the telephone with brief pauses between letters. The system uses separate neural networks to locate segment boundaries and classify letters. The letter scores are then used to search a database of names to find the best scoring name. The speaker-independent classification rate for spoken letters is 89%. The system retrieves the correct name, spelled with pauses between letters, 91% of the time from a database of 50,000 names.