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

Ejbali, Ridha; Zaied, Mourad; Amar, Chokri Ben

doi:10.14569/ijacsa.2012.030407

Cited by 18 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Introductionmentioning

confidence: 99%

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

ElAdel

Ejbali

Zaied

et al. 2016

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

Content-based image retrieval (CBIR) has been a worthwhile topic for research for several years. A powerful CBIR system should minimize the semantic gap between the low-level features and high-level concepts in order to satisfy users requirements. Moreover, it should take into consideration the execution time. In this paper, we present a new semantic approach for CBIR supported by a parallel aggregation of content-based features extraction (shape, texture, color) using fuzzy support decision mechanisms. Shape features are based on Fast Beta Wavelet Network modeling and Hue moments. The texture descriptor is based on Energy computing at different decomposition levels. Finally, we present an implementation of a new color feature extraction based on fuzzy indexed color map. In the second stage, we propose a Fuzzy Decision Support System for feature (shape, texture, color) aggregation to improve the retrieval performance. The proposed approach is tested on four most popular datasets: Wang, INRIA Holidays, UKBench and samples from ImageNet, and the experiments showed that B Asma ElAdel the proposed approach can achieve a satisfactory retrieval performance with an acceptable search time.

show abstract

Section: Introductionmentioning

confidence: 99%

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

ElAdel

Ejbali

Zaied

et al. 2016

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another improvement we are making to the model is to include a batch normalization [26], [27] layer to make it more reliable and efficient [6] [28]. Loffe and Szegedy introduce the batch normalization concept in 2015.…”

Section: Batch Normalizationmentioning

confidence: 99%

B-CNN: Betadeep Convolutional Neural Network over encrypted data

Issaoui,

ElAdel,

ZAIED

2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

The results of automatic learning algorithms based on deep neural networks are impressive, and they are extensively used in a variety of fields. However, access to private information, frequently sensitive to confidentiality (financial, medical, etc.), is required in order to use them. This calls for good precision as well as special attention to the privacy and security of the data. In this paper, we propose a novel approach to solve this issue by using Convolutional Neural Network (CNN) model over encrypted data. In order to achieve our contribution, we focus on approximating the often used activation functions that seem to be the key functions in CNN networks which are: ReLu, Sigmoid and Tanh. We start by creating a low-degree polynomial, which is essential for a successful homomorphic encryption (HE). This polynomial which is based on Beta function and its primitive will be used as an activation function. The next step is to build a CNN model using batch normalization to ensure that the data are contained inside a limited interval. Finally, MNIST is used in order to evaluate our methodology and assess the effectiveness of the proposed approach. The experimental results support the efficacy of the proposed approach.

show abstract

“…The divergence is described using a cost function. The cost function of an SAE consists of the following three terms (Hassairi et al, 2015;Ejbali et al, 2012):…”

Section: The Basic Sparse Auto-encodermentioning

confidence: 99%

Classification Program and Story Boundaries Segmentation in TV News Broadcast Videos via Deep Convolutional Neural Network

Hmayda¹,

Ejbali²,

Zaied³

2020

Journal of Computer Science

View full text Add to dashboard Cite

Given the amount of video information on the net, the user has had difficulty finding the information in a reasonable amount of time. Thus, all video content must be segmented and annotated so that he/she can access the information directly. The goal of the proposed approach is to allow a better exploitation of video by multimedia services (TV-On-Demand, catch-up TV), social community and video-sharing platforms (Youtube, Facebook…). In this work, an approach to classify TV programs and story boundaries segmentation in TV news broadcast video using Deep Convolutional Neural Network (DCNN) is presented. The first step is to extract features from video. This characteristics will modeled as video corpus governings the organization of TV stream content. This organization is carried out on two levels. The first consists in the identification of anchorperson by Single-Linkage Clustering through CNN faces and the second level aims to identify the story of news program due to the large audience because of the pertinent information they contain. In addition, we implement a 360-h broadcast video dataset obtained from five French news channels with ground-truth marked semantic shot categories, program genres and story boundaries. Experiments on this dataset prove the relevance of our approach for news broadcast video segmentation.

show abstract

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

Cited by 18 publications

References 22 publications

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

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

B-CNN: Betadeep Convolutional Neural Network over encrypted data

Classification Program and Story Boundaries Segmentation in TV News Broadcast Videos via Deep Convolutional Neural Network

Contact Info

Product

Resources

About