Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated from the run length matrix within each spin and the final feature vector is then used to populate a deep belief network for classification purpose. The proposed SISR system is evaluated using the English language Speech Database for Speaker Recognition (ELSDSR) database. The experimental results were achieved with 96.46 accuracy; showing that the proposed SISR system outperforms those reported in the related current research work in terms of recognition accuracy.
The manifestations of climate change are increasing with the days: sudden rains and floods, lakes that evaporate, rivers that experience unprecedentedly low water levels, and successive droughts such as the Tigris, Euphrates, Rhine, and Lape rivers. At the same time, energy consumption is increasing, and there is no way to stop the warming of the Earth's atmosphere despite the many conferences and growing interest in environmental problems. An aspect that has not received sufficient attention is the tremendous heat produced by human activities. This work links four elements in the built environment that are known for their high energy consumption (houses, supermarkets, greenhouses, and asphalt roads) according t
... Show MoreThe automatic estimation of speaker characteristics, such as height, age, and gender, has various applications in forensics, surveillance, customer service, and many human-robot interaction applications. These applications are often required to produce a response promptly. This work proposes a novel approach to speaker profiling by combining filter bank initializations, such as continuous wavelets and gammatone filter banks, with one-dimensional (1D) convolutional neural networks (CNN) and residual blocks. The proposed end-to-end model goes from the raw waveform to an estimated height, age, and gender of the speaker by learning speaker representation directly from the audio signal without relying on handcrafted and pre-computed acou
... Show MoreEnd of the twentieth century witnessed by the technological evolution Convergences between the visual arts aesthetic value and objective representation of the image in the composition of the design of the fabric of new insights and unconventional potential in atypical employment. It is through access to the designs of modern fabrics that address the employment picture footage included several scenes footage from the film, which focuses on research and analytical as a study to demonstrate the elements of the picture and the organization of its rules and how to functioning in the design of fabrics, Thus, it has identified the problem by asking the following: What are the elements of the picture footage and how the functioning of the struct
... Show MoreThe mobile services are the most important media between many of telecommunication means such as the Internet and Telephone networks, And thatis be cause of its advantage represented by the high availability and independence of physical location and time,Therefore, the need to protect the mobile information appeared against the changing and the misuse especially with the rapid and wide grow of the mobile network and its wide usage through different types of information such as messages, images and videos. The proposed system uses the watermark as tool to protect images on a mobile device by registering them on a proposed watermarking server. This server allows the owner to protect his images by using invisible wat
... Show MoreHuman skin detection, which usually performed before image processing, is the method of discovering skin-colored pixels and regions that may be of human faces or limbs in videos or photos. Many computer vision approaches have been developed for skin detection. A skin detector usually transforms a given pixel into a suitable color space and then uses a skin classifier to mark the pixel as a skin or a non-skin pixel. A skin classifier explains the decision boundary of the class of a skin color in the color space based on skin-colored pixels. The purpose of this research is to build a skin detection system that will distinguish between skin and non-skin pixels in colored still pictures. This performed by introducing a metric that measu
... Show MorePreparation of identical independent photons is the core of many quantum applications such as entanglement swapping and entangling process. In this work, Hong-Ou-Mandel experiment was performed to evaluate the degree of indistinguishability between independent photons generated from two independent weak coherent sources working at 640 nm. The visibility was 46%, close to the theoretical limit of 50%. The implemented setup can be adopted in quantum key distribution experiments carried out with free space as the channel link, as all the devices and components used are operative in the visible range of the electromagnetic spectrum.
The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recog
... Show More