Zero-crossing Rate Research Articles

Multi-format speech BioHashing based on energy to zero ratio and improved LP-MMSE parameter fusion

In order to solve the problems of poor security and small application scope of speech content authentication, and to improve the robustness, discrimination and real-time performance of speech authentication, a multi-format speech BioHashing algorithm based on energy to zero ratio and improved linear prediction minimum mean square error (LP-MMSE) parameter fusion is proposed. Firstly, the algorithm extracts the short-term logarithmic energy, zero-crossing rate and the covariance method’s LP-MMSE of speech signal to be processed. Then, the time-frequency parameters are fused, and the fused feature vector and the orthogonal normalized random matrix of the key control are generated into BioHashing sequences through the inner product form. Finally, the BioHashing is encrypted by equal-length scrambling using henon chaotic map. The experimental results show that the proposed algorithm not only has the characteristics of good discrimination, strong robustness, good security, high real-time performance and wide application range, but also realizes the detection and localization of small-scale tampering of speech through minimum code distance (MCD) algorithm. At the same time, the algorithm also validates the unidirectionality of BioHashing with trapdoor by comparative difference method.

An Improved Speech Segmentation and Clustering Algorithm Based on SOM and K-Means

This paper studies the segmentation and clustering of speaker speech. In order to improve the accuracy of speech endpoint detection, the traditional double-threshold short-time average zero-crossing rate is replaced by a better spectrum centroid feature, and the local maxima of the statistical feature sequence histogram are used to select the threshold, and a new speech endpoint detection algorithm is proposed. Compared with the traditional double-threshold algorithm, it effectively improves the detection accuracy and antinoise in low SNR. The k-means algorithm of conventional clustering needs to give the number of clusters in advance and is greatly affected by the choice of initial cluster centers. At the same time, the self-organizing neural network algorithm converges slowly and cannot provide accurate clustering information. An improved k-means speaker clustering algorithm based on self-organizing neural network is proposed. The number of clusters is predicted by the winning situation of the competitive neurons in the trained network, and the weights of the neurons are used as the initial cluster centers of the k-means algorithm. The experimental results of multiperson mixed speech segmentation show that the proposed algorithm can effectively improve the accuracy of speech clustering and make up for the shortcomings of the k-means algorithm and self-organizing neural network algorithm.

Efficient Noisy Sound-Event Mixture Classification Using Adaptive-Sparse Complex-Valued Matrix Factorization and OvsO SVM.

This paper proposes a solution for events classification from a sole noisy mixture that consist of two major steps: a sound-event separation and a sound-event classification. The traditional complex nonnegative matrix factorization (CMF) is extended by cooperation with the optimal adaptive L1 sparsity to decompose a noisy single-channel mixture. The proposed adaptive L1 sparsity CMF algorithm encodes the spectra pattern and estimates the phase of the original signals in time-frequency representation. Their features enhance the temporal decomposition process efficiently. The support vector machine (SVM) based one versus one (OvsO) strategy was applied with a mean supervector to categorize the demixed sound into the matching sound-event class. The first step of the multi-class MSVM method is to segment the separated signal into blocks by sliding demixed signals, then encoding the three features of each block. Mel frequency cepstral coefficients, short-time energy, and short-time zero-crossing rate are learned with multi sound-event classes by the SVM based OvsO method. The mean supervector is encoded from the obtained features. The proposed method has been evaluated with both separation and classification scenarios using real-world single recorded signals and compared with the state-of-the-art separation method. Experimental results confirmed that the proposed method outperformed the state-of-the-art methods.

Advanced Digital Signal Processing Techniques on the Classification of the Heart Sound Signals

Speech processing subject primarily depends on the digital signal processing (DSP) methods, such as convolution, discrete Fourier transform (DFT), fast Fourier transforms (FFT), finite impulse response (FIR) and infinite impulse response (IIR) filters, FFT recursive and non-recursive digital filters, FFT processing, random signal theory, adaptive filters, upsampling and downsampling, etc. Recursive and non-recursive digital filters are primarily deployed to absorb the signal of interest signals and to block the unwanted signals (noise). Broadly, low-pass, high-pass, band-pass, and band-stop filters are implemented for filtering functions. In frequent, the DSP theories can be used for further biomedical engineering domains like biomedical imaging (MRI, ultrasound, CT, X-ray, PET) and genetic signal analysis-cum-processing too. In this article, the experiments such as voiced/unvoiced detection, formants estimation using FFT and spectrograms, pitch estimation and tracking and yes/no sound classification are used. Also, the analysis of normal/abnormal heart sound signals using simple energy computation and the zero-crossing rate and their results are obtained. For the entire study, the Matlab R2018a tool is used to obtain the simulation results. At last, the criticism, feedbacks, comments, reactions from the student are detailed for the exceptional development of the course.

The detection of Parkinson disease using the genetic algorithm and SVM classifier

The speech signal is like the black box of human beings where much information is hidden. The treatment of this signal provides us with the speaker’s identity. In a way, it is similar to an identity card. Moreover, some neurologic diseases such as Alzheimer, depression, and Parkinson are detected based on the features extraction from the speech signals. In our study, we have recourse to the evolutionary algorithms such as the genetic algorithm GA, which is most commonly used in the making of a decision. The genetic algorithm intervenes with the Support vector machine SVM algorithm. This algorithm is a supervised machine learning that can be employed to design models defining important data classes, where class characteristics are involved in the construction of the classifier. In this article, a model of classification is proposed by the use of a discrete wavelet transform DWT to transform the signal. A Linear predictive coding LPC, energy, zero-crossing rate ZCR, Mel frequency cepstral coefficient MFCC, and wavelet Shannon entropy features are extracted from the approximation a3. Then by applying the GA and the classifier SVM, the best accuracy obtained was 91.18%.

Modeling and Optimization for Fault Diagnosis of Electromechanical Systems Based on Zero Crossing Algorithm

The demand of system security and reliability in the modern industrial process is ever-increasing, and fault diagnosis technology has always been a crucial research direction in the control field. Due to the complexity, nonlinearity, and coupling of multitudinous control systems, precise system modeling for fault diagnosis is attracting more attention. In this paper, we propose an improved method of electromechanical systems fault diagnosis based on zero-crossing (ZC) algorithm, which can present the calculation model of zero-crossing rate (ZCR) and optimize the parameters of ZC algorithm by establishing a criterion function model to improve the diagnosis accuracy and robustness of ZC characteristic model. The simulation validates the influence of different signal-to-noise ratio (SNR) on ZC feature recognition ability and indicates that the within-between distance model is effective to enhance the diagnose accuracy of ZC feature. Finally, the method is applied to the diagnosis of motor fault bearing, which confirms the necessity and effectiveness of the model improvement and parameter optimization and verifies the robustness to the load.

Fuzzy-based voiced-unvoiced segmentation for emotion recognition using spectral feature fusions

Despite abundant growth in automatic emotion recognition system (ERS) studies using various techniques in feature extractions and classifiers, scarce sources found to improve the system via pre-processing techniques. This paper proposed a smart pre-processing stage using fuzzy logic inference system (FIS) based on Mamdani engine and simple time-based features i.e. zero-crossing rate (ZCR) and short-time energy (STE) to initially identify a frame as voiced (V) or unvoiced (UV). Mel-frequency cepstral coefficients (MFCC) and linear prediction coefficients (LPC) were tested with K-nearest neighbours (KNN) classifiers to evaluate the proposed FIS V-UV segmentation. We also introduced two feature fusions of MFCC and LPC with formants to obtain better performance. Experimental results of the proposed system surpassed the conventional ERS which yielded a rise in accuracy rate from 3.7% to 9.0%. The fusion of LPC and formants named as SFF LPC-fmnt indicated a promising result between 1.3% and 5.1% higher accuracy rate than its baseline features in classifying between neutral, angry, happy and sad emotions. The best accuracy rates yielded for male and female speakers were 79.1% and 79.9% respectively using SFF MFCC-fmnt fusion technique.

Unsupervised and supervised VAD systems using combination of time and frequency domain features

Voice Activity Detection (VAD), also referred as Speech Activity Detection (SAD) is the process of identifying speech/non-speech region in digital speech recordings. It is used as a preliminary stage to reduce errors and increase effectiveness in the most of speech based applications like automatic speech recognition (ASR), speaker identification/verification, speech enhancement, speaker diarization etc. In this study, two independent VAD structures were proposed for unsupervised and supervised approaches using both time and frequency domain features. The autocorrelation based pitch contour estimation was used together with the 1NN Cosine classifier trained by 21-column feature matrix comprising Energy, Zero Crossing Rate (ZCR), 13rd order-Mel Frequency Cepstral Coefficients (MFCC) and Shannon Entropies of daubechies-filtered 5th depth-Wavelet Packet Transform (WPT) to obtain VAD decision in supervised approach, while methods like normalization, thresholding and median filtering were applied over the same feature set in unsupervised approach. The proposed unsupervised VAD achieved error rates of 4%, 19%, 0.02% and 0.7% for the FEC, MSC, OVER and NDS, respectively at 0 dB SNR. The VAD decisions of both supervised and unsupervised systems showed that the proposed methods can efficiently be used either in silent or in environments with noise similar to Additive White Gaussian Noise (AWGN).

Quantitative Analysis of Movements in Children with Attention-Deficit Hyperactivity Disorder Using a Smart Watch at School

Attention-deficit hyperactivity disorder (ADHD) is primarily diagnosed using set criteria and checklists. However, authors have indicated that such criteria and checklists are subjective. In this study, data from the gyroscope and accelerometer in a smart watch were used to analyze the movements of children with ADHD. This study cohort comprised 15 children with ADHD and 15 age- and sex-matched control participants. The children with ADHD and controls wore the watches on their non-writing hands simultaneously in class. The recordings of one patient and one control were tracked for 2 h daily for three consecutive days with desk and seated class activities. We compared the measurements of variance and the zero-crossing rate (ZCR) of the gyroscope and accelerometer between the children with ADHD and controls. All average variance and ZCR values of the three axes (x, y, and z) in the gyroscope and accelerometer were higher in children with ADHD than in the controls. Significant differences in average variance values on the y-axis (p < 0.001) and ZCR values on all three axes (x, p = 0.005; y, p = 0.003; and z, p = 0.004) of the gyroscope were observed. Similarly, significant differences in the average variance values on the three axes (x, p = 0.001; y, p < 0.001; and z, p < 0.001) and ZCR values on the z-axis (p = 0.006) of the accelerometer were observed. The proposed method is a promising tool to objectively analyze the movements of children with ADHD at school.

Recognition method research on rough handling of express parcels based on acceleration features and CNN

Abstract Rough Handling of Express Parcels (RHEP) increases the risk of courier cargo damage and hurts the reputation of the express industry. Meanwhile, RHEP indirectly caused excessive use of packaging materials and cushioning materials, thereby aggravating environmental and social problems, such as waste disposal pressure and waste of resources. The prerequisite to prevent RHEP is recognition of it. Three typical types of RHEP (dropping, kicking fast and throwing) are discussed in this paper. For these types of RHEP, an intelligent recognition method is proposed. The main idea is to window the acceleration data of the package and extract the features in the window, then arrange these feature data into a three-dimensional matrix as the input of the CNN, and finally obtain the recognition result. In the study, mean, variance, kurtosis, skewness, dynamic range, short-term energy, and zero-crossing rate were considered to be good features in the issues dealt with in this paper. The feature data are organized in a way that different features occupy different channels. Within the uniform channel, three rows correspond to three axes, and the time window order corresponds to consecutive columns. This arrangement of feature data can take full advantage of convolution operations to mine the potential information of acceleration signals with time series characteristics and spatial characteristics. Experimental results show that the recognition accuracy of this method can reach 93.2% -96.12% steadily, which is better than the performance of directly arranging features into vectors and sending it to the fully connected network (recognition accuracy is 85% -95% and fluctuates greatly). Combining the recognition results of this method with the time and place of RHEP can more clearly analyze the causes of RHEP and propose targeted preventive measures.

A Novel Quantitative Spasticity Evaluation Method Based on Surface Electromyogram Signals and Adaptive Neuro Fuzzy Inference System.

Stroke patients often suffer from spasticity. Before treatment of spasticity, there are often practical demands for objective and quantitative assessment of muscle spasticity. However, the common quantitative spasticity assessment method, the tonic stretch reflex threshold (TSRT), is time-consuming and complicated to implement due to the requirement of multiple passive stretches. To evaluate spasticity conveniently, a novel spasticity evaluation method based on surface electromyogram (sEMG) signals and adaptive neuro fuzzy inference system (i.e., the sEMG-ANFIS method) was presented in this paper. Eleven stroke patients with spasticity and four healthy subjects were recruited to participate in the experiment. During the experiment, the Modified Ashworth scale (MAS) scores of each subject was obtained and sEMG signals from four elbow flexors or extensors were collected from several times (4–5) repetitions of passive stretching. Four time-domain features (root mean square, the zero-cross rate, the wavelength and a 4th-order autoregressive model coefficient) and one frequency-domain feature (the mean power frequency) were extracted from the collected sEMG signals to reflect the spasticity information. Using the ANFIS classifier, excellent regression performance was achieved [mean accuracy = 0.96, mean root-mean-square error (RMSE) = 0.13], outperforming the classical TSRT method (accuracy = 0.88, RMSE = 0.28). The results showed that the sEMG-ANFIS method not only has higher accuracy but also is convenient to implement by requiring fewer repetitions (4–5) of passive stretches. The sEMG-ANFIS method can help stroke patients develop proper rehabilitation training programs and can potentially be used to provide therapeutic feedback for some new spasticity interventions, such as shockwave therapy and repetitive transcranial magnetic stimulation.

Developing a Deep Learning Sound Classification System for a Smart Farming

The Internet of Things (IoT) and Machine Learning (ML) are a promising technologies for automation in the different domains e.g. Smart Farming. Such systems could be used for determining noise emission, animal detection and classification, monitoring states of bees in beehive and etc. As rule the characteristics of that systems are some controversial: compactness (deploying on the single-board computers) and real time classification and prediction. Therefore, the software for IoT and ML applications should be sufficiently efficient and not demanding on large computing resources. This work are focused on machine hearing system allows to classify natural sounds in the Smart Farming software application.The original acoustic signal is converted to the frames of a certain length. Receiving a compact representation of the acoustic characteristics of a signal is the aim of the feature extraction stage. This stage exploits special coefficients such as Zero-crossing rate, Spectrum shape, Short-Time Fourier Transform and Mel-frequency cepstral coefficients. Audio classification traditionally involves such machine learning methods as K-means, support vector machine (SVM), decision trees etc. Deep neural networks can be used on both raw acoustic signal and features extracted from it. The accuracy estimation stage deploys quality assessment methods.The data preprocessing stage includes calculating of mel frequency cepstral coefficient (MFCC) for the giving sound files. This approach allows to unify and simplify the sound files presentation in the memory. Further MFCC arrays are feeding to the convolutional neural net. It is important at this stage to configure the network optimally for the most compact storage. This is due to the need to use platforms such as Raspberry Pi to deploying neural network.For neural network software implementation Python library Keras is used. For data preprocessing Python library Librosa is used. The hyperparameters of the neural network have been defined in computational experiments and the optimal combination is two Conv2D layers and three Dense layers.The accuracy of model predictions for each class has been examined by using a confusion matrix and the satisfactory classification accuracy has been defined.It has been established the convolutional neural network ensemble built to solve the problem of acoustic data classification is quite effective. The accuracy of the model on the test data is 95%. It should be noted that the neural network structure with only two packets of convolution-activation-sub-sampling layers was sufficient to solve this problem. The system can be used in Smart Farming applications to filter out unnecessary sounds.

Vocal Data Assesment To Envision Distinctive Features of An Individual

There is a lot of audio data generated on a day to day bases, which goes to waste without undergoing due processing. If we process this data, it can be beneficial for a multitude of purposes. Vocal data is unstructured, which makes it even harder for processing. This data has to undergo thorough pre-processing to convert it to a machine-understandable form. We aim to perform analysis of human voice to extract meaningful data and make a prediction of their age, gender, and accent. The developed system uses the Mel-frequency Cepstral Coefficient (MFCC), zero-cross-rate(ZCR), chroma_stft, spectral_centroid, spectral_bandwidth, and spectral_rolloff algorithms as a tool for Feature Extraction. The algorithms used for making inferences are support vector machine (SVM), K-nearest neighbors, and SVR. The work can be extended even further by combining video data with the audio data for analysis. The system can also be improved by increasing the number of languages it can detect.

Automatic and manual extraction of speech and language characteristics associated with depression

Early and accurate diagnosis and intervention of depression is important to facilitate timely, direct, and appropriate interventions with potential for improved clinical outcomes. Delays in the diagnosis of patients with depression may be reduced if simple tools were available to indicate probability of diagnosis. Clinicians use speech and language characteristics to establish current mental state and diagnosis. The use of automatic acoustic feature extraction allows leveraging pitch, power, and variability and can provide an unbiased evaluation of speech.
 This study examined speech samples from a youth at-risk cohort, aged 9-25, and developed a manual rating system of speech and language characteristics, which involved rating short segments of audio and transcript on emotion, sentiment, affect, and richness. This competed against an automated model of extracting zero-crossing rate, energy, the entropy of energy, and Mel-frequency cepstral coefficients to identify speech characteristics associated with major depressive disorder.
 The results showed that the automatic feature extraction outcompeted the manual rating system in explaining the difference in speech between participants with and without major depressive disorder through speech and language characteristics. While the extraction of audio features is not a substitute for the clinical interview, the ability to provide an unbiased prediction of vulnerability to depression from speech may assist clinicians in early diagnosis.

Discrimination of Low-set Tongue Using Zero-crossing Rates and Mel Frequency Cepstrum Coefficients for Quantification of Pronunciation Speech

Discrimination of Low-set Tongue Using Zero-crossing Rates and Mel Frequency Cepstrum Coefficients for Quantification of Pronunciation Speech

An acoustic emission activity detection method based on short-term waveform features: Application to metallic components under uniaxial tensile test

The Acoustic Emission (AE) phenomenon has been used as a powerful tool with the purpose to either detect, locate or assess damage for a wide range of applications. Derived from its monitoring, one major current challenge on the analysis of the acquired signal is the proper identification and separation of each AE event. Current advanced methods for detecting events are primarily focused on identifying with high accuracy the beginning of the AE wave; however, the detection of the conclusion has been disregarded in the literature. For an automatic continuous detection of events within a data stream, this lack of accuracy for the conclusion of the events generates errors in two critical aspects. In one hand, it deteriorates the accuracy of the measurement of the events duration, truncating the span of the event, which is undesirable in evaluation applications; and in the other hand, it causes false detections. In this work, an accurate and computationally efficient AE activity detector is presented, using a framework inspired by the area of speech processing, and which provides the required indicators to accurately detect the onset and the end of an AE event. This is achieved by means of a threshold approach that instead of directly operates with the transduced voltage signal it does so over the Short-Term Energy and the Short-Term Zero-Crossing Rate measures of the signal. The STE-ZCR method is developed for an application related to the continuous monitoring of a single AE channel derived from the characterization of metallic components by means of a uniaxial tensile test. Additionally, two experimental test-benches are implemented with the aim to quantify the accuracy and the quality of event detection of the presented method. Finally, the obtained results are compared with four different techniques, representing the current state of the art related to AE activity detection.

Forecasting Fluctuations in the Financial Index Using a Recurrent Neural Network Based on Price Features

Profits can be made from a trading strategy where long or short positions are placed in advance, based on the ability to forecast a future stock price or index, such as the closing or opening price. In addition to predicting stock index values, a prediction of the sign for the difference between closing and opening prices is important in order to earn a profit. This article presents an approach based on a Recurrent Neural Network (RNN) to forecast the opening price, the closing price, and the difference between them. Compared to previously reported approaches that were based on machine learning, the method proposed here emphasizes the pre-processing of the data, including the normalized first order difference method, as well as the focusing on the characteristics of the stock data, such as the zero-crossing rate (ZCR), which denotes the ratio of changes in the sign within a specific time interval. We propose a decision-making approach that is based on an estimate of both the ZCR and the cross-validation data so as to enhance the ability to forecast the difference between the opening and closing prices. We apply our technique to the S&P500 (Standard & Poor's 500) and the Dow Jones stock indices. As indicated by the results, our method can achieve a better performance compared to previous work.

Motion Artifact Suppression for Insulated EMG to Control Myoelectric Prostheses.

Myoelectric prostheses help amputees to regain independence and a higher quality of life. These prostheses are controlled by electromyography, which measures an electrical signal at the skin surface during muscle contractions. In this contribution, the electromyography is measured with innovative flexible insulated sensors, which separate the skin and the sensor area by a dielectric layer. Electromyography sensors, and biosignal sensors in general, are striving for higher robustness against motion artifacts, which are a major obstacle in real-world environment. The motion artifact suppression algorithms presented in this article, prevent the activation of the prosthesis drive during artifacts, thereby achieving a substantial performance boost. These algorithms classify the signal into muscle contractions and artifacts. Therefore, new time domain features, such as Mean Crossing Rate are introduced and well-established time domain features (e.g., Zero-Crossing Rate, Slope Sign Change) are modified and implemented. Various artificial intelligence models, which require low calculation resources for an application in a wearable device, were investigated. These models are neural networks, recurrent neural networks, decision trees and logistic regressions. Although these models are designed for a low-power real-time embedded system, high accuracies in discriminating artifacts to contractions of up to 99.9% are achieved. The models were implemented and trained for fast response leading to a high performance in real-world environment. For highest accuracies, recurrent neural networks are suggested and for minimum runtime (0.99–1.15 s), decision trees are preferred.

Hyperspectral monitoring of maize leaves under copper stress at different growth stages

ABSTRACTUsing hyperspectral remote sensing technology to identify spectral changes of crop leaves under heavy metal pollution is an important way to ensure food security. Discrete Fourier transform (DFT) and discrete wavelet transform (DWT) are used to rapid screen the spectral characteristics of maize growth status under copper (Cu) stress, and a zero-crossing rate (ZCR) was proposed to quantify the results. The experiment of maize under different Cu stress treatment was carried out, and the spectra of maize leaves at seedling, jointing and heading stages were measured. Analysis of frequency spectrum and amplitude spectrum of the maize leaves spectra under copper stress showed that the growth stages of maize could be effectively determined according to the phase of leaves spectra. The approximate coefficient (CA) and detail coefficient (CD) were obtainedat heading stage. It was found that the wavelength corresponding to the peak value of the acquired variable of CA (ca) in the range of 690–710 nm was moving in the direction of shortwave. In addition, the degree of copper stress in maize could be divided according to the peak deviation of ca. The characteristic wavebands could be detected according to the CD variable (cd) .

Feature extraction algorithms to improve the speech emotion recognition rate

In this digitally growing era speech emotion recognition plays significant role in several applications such as Human Computer Interface (HCI), lie detection, automotive system to assist steering, intelligent tutoring system, audio mining, security, Telecommunication, Interaction between a human and machine at home, hospitals, shops etc. Speech is a unique human characteristic used as a tool to communicate and express one’s perspective to others. Speech emotion recognition is extracting the emotions of the speaker from his or her speech signal. Feature extraction, Feature selection and classifier are three main stages of the emotion recognition. The main aim of this work is to improve the speech emotion recognition rate of a system using the different feature extraction algorithms. The work emphasizes on the preprocessing of the received audio samples where the noise from speech samples is removed using filters. In next step, the Mel Frequency Cepstral Coefficients (MFCC), Discrete Wavelet Transform (DWT), pitch, energy and Zero crossing rate (ZCR) algorithms are used for extracting the features. In feature selection stage Global feature algorithm is used to remove redundant information from features and to identify the emotions from extracted features machine learning classification algorithms are used. These feature extraction algorithms are validated for universal emotions comprising Anger, Happiness, Sad and Neutral.