Proceedings ArticleDOI
Modular connectionist structure for 100-word recognition
H. Hackbarth,J. Mantel +1 more
- pp 845-849
Reads0
Chats0
TLDR
Under the criterion of high recognition rates along with very short reaction time, modular subnet assemblies provide for successful recognition of 100 words and are also recommended for speaker-independent classification.Abstract:
A modular neural structure is presented which is dedicated to the recognition of larger vocabularies. It contains several so-called scaly subnets, assembled into a compound network by neural glue elements. This architecture and the corresponding training scheme have been investigated for various network parameters during speaker-dependent 100-word recognition. Important simulation results were compared with a multilayer perceptron showing scaly input-to-hidden connections and with standard dynamic time warping. Under the criterion of high recognition rates along with very short reaction time, modular subnet assemblies provide for successful recognition of 100 words. They are also recommended for speaker-independent classification. >read more
Citations
More filters
Journal ArticleDOI
Modular neural networks: a survey.
Gasser Auda,Mohamed S. Kamel +1 more
TL;DR: The different motivations for creating MNNs are surveyed: biological, psychological, hardware, and computational, and the general stages of MNN design are outlined and surveyed, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies.
Dissertation
Biologically Inspired Modular Neural Networks
TL;DR: This dissertation presents an in depth study of the currently available modular neural network architectures along with highlighting their shortcomings and investigates new modular artificial neural network models in order to overcome pointed out shortcomings.
Journal ArticleDOI
Modular Neural Network Classifiers: A Comparative Study
Gasser Auda,Mohamed S. Kamel +1 more
TL;DR: Ten MNN classifiers which give a good representation of design varieties are compared and the strength-points and drawbacks of the different networks are outlined to help a potential user to choose an appropriate model according to the application in hand and the available computational resources.
Journal ArticleDOI
CMNN: cooperative modular neural networks for pattern recognition
Gasser Auda,Mohamed S. Kamel +1 more
TL;DR: Compared to previous modular designs, a significant enhancement in the efficiency of the modular structure is noticed and CMNN's trade-off is a slight increase in the required computational work as compared to some models.
Journal ArticleDOI
Modular neural networks with applications to pattern profiling problems
H. Chris Tseng,Bassam Almogahed +1 more
TL;DR: This study validates that modular design is a promising solution for large-scale soft computing problems by decomposing the given pattern profiling problem into smaller modules and showing that comparable performance can be achieved with improvement on computation and design complexity.
References
More filters
Proceedings ArticleDOI
Continuous speech recognition using multilayer perceptrons with hidden Markov models
Nelson Morgan,Hervé Bourlard +1 more
TL;DR: A phoneme based, speaker-dependent continuous-speech recognition system embedding a multilayer perceptron (MLP) into a hidden Markov model (HMM) approach is described, which appears to be somewhat better when MLP methods are used to estimate the probabilities.
Proceedings ArticleDOI
Large vocabulary recognition using linked predictive neural networks
J. Tebelskis,Alex Waibel +1 more
TL;DR: In this system, neural networks are used as predictors of speech frames, enabling a pool of such networks to serve as phoneme models, and the LPNN is vocabulary independent and can be applied to large-vocabulary recognition.
Proceedings ArticleDOI
Phonetic typewriter for Finnish and Japanese
TL;DR: A microprocessor-based real-time speech recognition system that is able to produce orthographic transcriptions for arbitrary words or phrases uttered in Finnish or Japanese and can also be used as a large-vocabulary isolated word recognizer.
Neural Networks for Speaker-Independent Recognition of Isolated Words
TL;DR: In this paper, a scaly pattern of connecting links between the input and hidden layer was established within a strict feed-forward wiring structure for speaker-independent recognition of isolated words from variable-size vocabulary.
Proceedings ArticleDOI
Scaly artificial neural networks for speaker-independent recognition of isolated words
A. Krause,H. Hackbarth +1 more
TL;DR: Artificial neural networks were investigated as an approach to speaker-independent recognition of isolated words from a variable-size vocabulary and showed good results.