Frequency Cepstral Coefficient Feature Extraction Research Articles

Classification of lung disorders based on lung sounds using deep learning

Treatment of lung sicknesses, that are the 0.33 maximum not unusual place reason of demise within side the world, is of high-quality significance within side the clinical field. Many research the use of lung sounds recorded with stethoscope had been carried out within side the literature so as to diagnose the lung sicknesses with synthetic intelligence-well suited gadgets and to help the professionals of their diagnosis [5]. Lung sounds carry applicable records associated to pulmonary problems, and to assess sufferers with pulmonary conditions, the medical doctor or the medical doctor makes use of the conventional auscultation method. How-ever, this method suffers from limitations. For example, if the medical doctor is not properly trained, this will result in a incorrect diagnosis. Moreover, lung sounds are non-stationary, complicating the duties of analysis, popularity, and distinction. This is why growing computerized popularity structures can assist to address those limitations [1].Classification of lung sounds on the earliest may be very important to customize their treatment. In this project, the lung problems are categorized primarily based totally on the time, frequency in addition to photograph capabilities extracted from auscultatory datasets and categorized the use of deep gaining knowledge of method. The set of rules used is a Convolutional Neural Network the use of Mel Frequency Cepstral Coefficient feature extraction.

Deep Learning Bidirectional LSTM based Detection of Prolongation and Repetition in Stuttered Speech using Weighted MFCC

Stuttering is a neuro-development disorder during which normal speech flow is not fluent. Traditionally Speech-Language Pathologists used to assess the extent of stuttering by counting the speech disfluencies manually. Such sorts of stuttering assessments are arbitrary, incoherent, lengthy, and error-prone. The present study focused on objective assessment to speech disfluencies such as prolongation and syllable, word, and phrase repetition. The proposed method is based on the Weighted Mel Frequency Cepstral Coefficient feature extraction algorithm and deep-learning Bidirectional Long-Short term Memory neural network for classification of stuttered events. The work has utilized the UCLASS stuttering dataset for analysis. The speech samples of the database are initially pre-processed, manually segmented, and labeled as a type of disfluency. The labeled speech samples are parameterized to Weighted MFCC feature vectors. Then extracted features are inputted to the Bidirectional-LSTM network for training and testing of the model. The effect of different hyper-parameters on classification results is examined. The test results show that the proposed method reaches the best accuracy of 96.67%, as compared to the LSTM model. The promising recognition accuracy of 97.33%, 98.67%, 97.5%, 97.19%, and 97.67% was achieved for the detection of fluent, prolongation, syllable, word, and phrase repetition, respectively.

Implementation of speech feature extraction for low‐resource devices

Feature extraction is an important function in the speech recognition system. Employing a speech recognition system in low-resource devices (LRDs) have increased significantly in recent years. Implementing feature extraction, which involves complex computations, in LRD is very challenging because LRD has limited energy, storage, and processing power. The optimum design must carefully balance performance metrics, including speed, area, and energy. The objective of this research is to implement and model speech feature extraction design in a field-programmable gate array (FPGA) platform, and to identify the optimum implementation for low-resource devices (LRDs). The novelty of this research is optimising feature extraction implementations using design options such as word size; and developing accurate performance models to enhance future designs. The authors study extensively examines the effect of fixed-point n -bit word size on the design of Mel frequency cepstral coefficients feature extraction in the FPGA implementation. The results show that the performance metrics (area, power, and energy) increase at a slower pace compared with n because the dependency of some blocks (e.g. logarithm) on n is non-linear. For example, increasing n by 50% increases the resource utilisation by 38%, power by 41% and energy by 41%. Models for resources, power, and energy are developed with accuracies of 5.1, 4.5, and 4.3%, respectively. Furthermore, n has a weak impact on timing results and therefore speed is almost similar across implementations. Each bit (in n ) costs 690 logical elements in the area, 2.35 mW in power and 0.55μJ in energy. For LRD, the 32-bit design demonstrates the most optimum design, followed by 48-bit and 24-bit designs.

Optimal Feature Selection Technique for Mel Frequency Cepstral Coefficient Feature Extraction in Classifying Infant Cry with Asphyxia

<p>Mel Frequency Cepstral Coefficient is an efficient feature representation method for extracting human-audible audio signals. However, its representation of features is large and redundant. Therefore, feature selection is required to select the optimal subset of Mel Frequency Cepstral Coefficient features. The performance of two types of feature selection techniques; Orthogonal Least Squares and F-ratio for selecting Mel Frequency Cepstral Coefficient features of infant cry with asphyxia was examined. OLS selects the feature subset based on their contribution to the reduction of error, while F-Ratio selects them according to their discriminative abilities. The feature selection techniques were combined with Multilayer Perceptron to distinguish between asphyxiated infant cry and normal cry signals. The performance of the feature selection methods was examined by analysing the Multilayer Perceptron classification accuracy resulted from the combination of the feature selection techniques and Multilayer Perceptron. The results indicate that Orthogonal Least Squares is the most suitable feature selection method in classifying infant cry with asphyxia since it produces the highest classification accuracy.<em></em></p>

Comparative Analysis of the Mel Frequency Cepstral Coefficients for Voiced and Silent Speech

The extraction of representative characteristics from voice signals, is the basic step for any application where speech signal processing is performed. In this paper, a comparative analysis of the Mel frequency cepstral coefficients, extracted from samples of voiced and silent speech is exposed. The classical methodology for extracting Mel frequency cepstral coefficient is evaluated to show the implementation steps and the robustness of such kind of features representing in a unique form the statistical and representative information of time varying signals. To achieve this comprehensive evaluation, first, a contextualization in theoretical terms of the methodology is performed to show the mathematical basis for the coefficient extraction. Each step of the process is analyzed in terms of the representative information of the coefficients. Therefore an evaluation in comparative terms against the previous developments for data interpretation is done. The coefficients are extracted using the classical implementation of the Mel frequency cepstral coefficient feature extraction process in a free software framework implemented in Matlab®. The results show the robustness of the Mel frequency cepstral coefficient algorithm in the characterization of voiced and silent speech signals, which represents an advantage for the construction of any kind of speech processing systems.

Palmprint recognition based on Mel frequency Cepstral coefficients feature extraction

Palmprint identification is a measurement of palmprint features for recognizing the identity of a user. Palmprint is universal, easy to capture and it does not change much across time. This paper presents an application of Mel frequency Cepstral coefficients (MFCCs) for identification of palmprint. Palmprint feature extraction is based on transforming the palmprint image into one dimensional (1-D) signal and then extracting MFCCs from this signal. Wavelet transform (DWT) of the 1-D palmprint signals are used for extracting additional features to help in the recognition process. The features from MFCCs of this DWT vector are added to the MFCCs feature vector, generated from the original palmprint signal, to form a large feature vector that can be used for palmprint identification. Feature matching is performed in this research using feed forward back propagation error neural network. Experimental results show that the proposed method is robust in the presence of noise.