In this paper, the Discrete Wavelet Transform is studied in purifying the sound signal from noise because of the good capabilities in this scope, especially when it is merged with both types of the (Thresholding), the solid and the flexible. The aim of this research is making comparisons between the types of deferent Discrete Wavelet Transform for both the filters which are used (Harr, Daubechies) in deferent levels (2, 3, 4, 5) with the additive of two types of noise to these filters (Gaussian White Noise) and (Random Noise). The decibel value that added to these filters was in the (5dB,10dB,15dB) values. Good results of the purification process are achived after computing the (Signal to Noise Ratio (SNR)) and (Mean Sequre Error (MSE)).
The most important aspect of human communication is speech. Lengthy media such as speech takes a long time to read and understand. This difficulty is solved by providing a reduced summary with semantics. Speech summarization can either convert speech to text using automated speech recognition (ASR) and then build the summary, or it can process the speech signal directly and generate the summary. This survey will look at a various of recent studies that have used machine and deep learning algorithms to summarize speech. it discusses the speech summarizing literatures in terms of time restrictions, research methodology, and lack of interest in particular databases for literature searches. As newer deep learning approaches were not included in earlier surveys, this is a new survey in this discipline where different approaches with various datasets were explored for speech summarization and evaluated using subjective or objective methods.
This study aims at constructing an intelligent system for recognizing the single Arabic numbers. It consists of two basic stages: the stage of features extraction and the stage of recognition. In the first stage, the technology of (Mel-Frequency cestrum coefficient (MFCC)) was employed. But in the second stage, the genetic algorithm was used. The results of the test showed that words recognition percentage was (100%) for the words used with training, and it was (97%) for the words used with no training. The proposed system was constructed using the MatLab version (0.7) program, and the data used in the system are the following numbers: (0, 1, 2, 3, 4, 5, 6, 7, 8 and 9). Also, six speakers (four males and two females) performed the voice recording.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.