Efficient MLP constructive training algorithm using a neuron recruiting approach for isolated word recognition system

Abstract

This paper describes an efficient constructive training algorithm using a Multi Layer Perceptron (MLP) neural network dedicated for Isolated Word Recognition (IWR) systems. Incremental training procedure was employed and this approach was based on novel hidden neurons recruiting for a single hidden-layer. During Neural Network (NN) training phase, the number of pronunciation samples extracted from the Training Data (TD) was sequentially increased. Optimal structure of the NN classifier with optimized TD size was obtained using this proposed MLP constructive training algorithm. Isolated word recognition system based on MLP neural network was then constructed and tested for recognizing ten words extracted from TIMIT database. Mel Frequency Cepstral Coefficient (MFCC) feature extraction method was employed including energy, first and second derivative coefficients.A proposed Frame-by-Frame Neural Network (FFNN) classification method was explored and compared with the Conventional Neural Network (CNN) classification approach. Principal Component Analysis (PCA) technique was also investigated in order to reduce both TD size as well as recognition system complexity.Experimental results showed superior performance of the proposed FFNN classifier compared to the CNN counter S. Masmoudi ( ) · M. Frikha · A.B. Hamida Technologie de l'information et électronique médicale,

A Comparitive Survey of ANN and Hybrid HMM/ANN Architectures for Robust Speech Recognition

“…The phone recognizer was trained and tested with TIMIT database [20]. All trainings were carried out using 100 phonemes of clean data.…”

“…Multilayer perceptrons (MLP) are the best studied class of ANN frequently applied in speech recognition [20]. They have layered feedforward architecture with an input layer, zero or more hidden layers and an output layer, as shown in Figure 4.…”

“…Artificial Neural Networks (ANN) and more specifically multilayer perceptrons (MLP) appeared to be a promising alternative in this respect to replace or help HMM in the classification mode. So, a number of ANN approaches have been suggested and used to improve the state of the art of ASR systems [20], [24]. The fundamental advantage of such approach is that it introduces a discriminative training [18].…”

Face recognition based on perceived facial images and multilayer perceptron neural network using constructive training algorithm

“…Over the learning process, the hidden neuron number is increased when the MSE threshold of the TD does not reach a predefined parameter called ε. Input patterns are learned incrementally subset by subset until all patterns ( N_tot ) of TD are presented [15].…”

“…The proposed constructive training algorithm is based on the one presented in [7] with deep improvements consisting on modifying the training pedagogy, determining the adequate value of the mean square error (MSE) threshold and the suitable initial hidden neurons number. The proposed algorithm has been applied for speech recognition problem [15] and the face recognition problem will be considered in this study.…”