Wavelet network for recognition system of Arabic word

Abstract

Focusing on the development of new technologies of information, research in the speech communication field is an activity in full expansion. Several disciplines and skills interact in order to improve performance of Human Machine Communication Systems (HMC). In order to increase the performance of these systems, various techniques, including Hidden Markov Models (HMM) and Neural Network (NN), are implemented.In this paper, we advance a new approach for modelling of acoustic units and a new method for speech recognition, especially recognition of Arabic word, adapting to this new type of modelling based on Wavelet Network (WN). The new recognition system is a hybrid classifier. It is based on NN as a general model and the wavelets assume the role of activation function.Our approach of speech recognition is divided into two parts: training, and recognition phases. The training stage is based on audio corpus. After converting all training signals from original format to a specific parameterisation, each acoustic vector will be modelled by WN. These vectors will refine and cover all signal properties in one model. It consists in generating a WN for every training signal. The recognition phase is divided into three steps. The first is to extract features from the input vector to be recognized. The second is to estimate all resulting vectors from training WN.The third is to evaluate the distance between the vector to be recognized and the reconstructed vectors.The obtained results shows that our system, based on WN, is very competitive compared to systems based on HMM.

A hybrid approach for Content-Based Image Retrieval based on Fast Beta Wavelet network and fuzzy decision support system

“…Since Beta wavelet [1] is a powerful tool in various domains such as image compression [2], face recognition [3,4], 3D face recognition [5], image classification [6,7], phoneme recognition [8], speech recognition [9] and in particular Arabic word recognition [10] and hand tracking and recognition [11]; this study used the Fast Beta Wavelet Network (FBWN) modeling to propose a new approach for CBIR.…”

Multi-input Multi-output Beta Wavelet Network: Modeling of Acoustic Units for Speech Recognition

“…To test the new architecture of modelling of acoustic units of speech, we have implemented a recognition system of Arabic word [4]. The results of this approach, MIMOWN, of modelling was compared to results given by a recognition system of Arabic words based on Hidden Markov Models HMM [14], [15] and the old architecture of Wavelet Network WN.…”

Acoustic modeling problem for automatic speech recognition system: advances and refinements (Part II)

“…To overcome the limitations of Gaussians mixture models, a new approach based on wavelet network was proposed in Ejbali et al (2010), showing better results compared to typical HMM based systems. Experiments were performed on 31 Arabic words using MFCC and PLP both at front end.…”