The use of wavelet transformation in conjunction with a heuristic algorithm as a tool for feature extraction from signals

Abstract

The use of algorithms is helpful in analysis of various data samples. Examples of these applications are sound and graphic processing that are used in authentication and analysis of images. In this work, we propose technique of extracting data from image file created based on voice sample. Proposed method makes use of mathematical model of wavelet transformation and its graphical visualization like scaleogram combined with computational intelligence methods like neural network and heuristic algorithm. In order to verify operation of proposed technique we present experimental results.

Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features

“…Current research in the computer science field focuses on replicating the analysis of SLP with assistive devices [8]- [11], adapting heuristic algorithms [12], [13] and deep learning [14]- [16] for monitoring change in speech patterns, speech recognition and classification [17]- [20]. In addition, wavelet transforms (discrete, continuous, tunable-Q) are successfully utilized for speech impairment monitoring based on voice signal analysis [21], [22]. Here we focus on adopting bidirectional recurrent neural network (BiRNN) with long shortterm memory (LSTM) [23], [24] and wavelet scattering transform-Gabor [25]) methods for solving healthy vs. impaired test subject classification problem based on speech signals.…”