Scaly artificial neural networks for speaker-independent recognition of isolated words

Krause, Anna; Hackbarth, Heidi

doi:10.1109/icassp.1989.266353

Cited by 18 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Krause and Hackbarth [2] showed that using a scaly type architecture to reduce the total number of connections in a network supported high recognition rates for isolated word recognition. Here the scaly architecture is applied between the input layer and the hidden layer as shown in Fig.…”

Section: The Scaly Neural Architecturementioning

confidence: 99%

A scaly artificial neural network architecture for isolated word recognition using the British Telecommunications English alphabet database

Creaney¹,

Naguib²

IEEE International Conference on Neural Networks

View full text Add to dashboard Cite

The use of neural networks for the recognition of isolated letters from the English Alpbabet is investigated. A scaly architecture neural network model is used and is trained using the error back propagation algorithm. ' b o different methods of non-linear time alignment are used and the performance of the neural networkwhenused with each compared.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. Variance of the learning rate in the error back propagation algorithm is investigated by comparing the performance of the neural network when three different valuesof learning rate are used.

show abstract

Section: The Scaly Neural Architecturementioning

confidence: 99%

A scaly artificial neural network architecture for isolated word recognition using the British Telecommunications English alphabet database

Creaney¹,

Naguib²

IEEE International Conference on Neural Networks

View full text Add to dashboard Cite

show abstract

“…After time normalization into 40 feature vector sized units, speaker dependent word classification is done using a previously aained neural network with "scaly" architecture. description of this network as well as its word recognition results is contained in [7]. The architecture of the test environment is depicted in figure 1.…”

Section: Data Base and Test Environmentmentioning

confidence: 99%

Neural network development for noise reduction in robust speech recognition

Trompf

[Proceedings 1992] IJCNN International Joint Conference on Neural Networks

View full text Add to dashboard Cite

Speech recognition systems with small and medium vocabulary are used as natural human interface in a variety of real world applications. Though they work well in a quiet environment, a significant loss in recognition performance can be observed in noise-contaminated real world applications. In order to make such a system more robust, the development of a neural network based noise reduction module is described in this paper. Using standard feedforward networks, several topologies have been tested to learn about the properties of neural noise reduction. For the develop ment of a sufficiently robust nonadaptive system, information about the characteristics of the noise and speech components of the input signal including context information was taken into account. This paper is focused on the stepwise experiment-oriented improvement of a basic linear neural noise reduction network. Evaluation of each step is done by a real world speech recognition task and includes experiments with changing input signal characteristics to test the robustness of this system. 0-7803-0559-0 192 $3.00 0 1992 IEEE

show abstract