Zero-crossing Rate Research Articles

Snore Signal Enhancement and Activity Detection via Translation-Invariant Wavelet Transform

Acoustical properties of snores have been widely studied as a potentially cost-effective and reliable alternative to diagnosing obstructive sleep apnea (OSA), with a common recognition that the diagnostic accuracy depends heavily on the snore signal quality and intelligibility. This paper proposes a novel preprocessing system that performs two critical tasks concurrently in a translation-invariant wavelet transform domain. These tasks include enhancement of snore signals via a level-correlation-dependent (LCD) threshold, and identification of snore presence through a snore activity (SA) detector. Various experiments were conducted to warrant the robustness of the system in terms of theoretical statistics quality, signal-to-noise ratio, mean opinion score, and clinical usefulness in detecting OSA. Results indicate that the proposed LCD threshold and SA detector are highly comparable to the existing denoising methodologies using level-dependent threshold and segmentation approaches using short-time energy and zero-crossing rate, yielding the best results in all the experiments. Given the strong initial performance of the proposed preprocessing system for snore signals, continued exploration in this direction could potentially lead to additional improvement in signal integrity, thereby increasing the diagnostic accuracy for OSA.

Subjective, cardiovascular and EMG spectral recovery after lumbar extension exhaustion test

The purpose of this randomized study was to evaluate EMG spectral, subjective and cardiovascular recovery parameters after isometric lumbar extension contractions. Ten healthy women performed isometric lumbar extensions until exhaustion with 5%, 10%, 15% and 20% of maximal voluntary isometric contr action on 4 different days (random order). One baseline five second contraction was performed before the fatiguing task which was followed by eight submaximal five second extension contractions (until 20 minutes after the end of the fatiguing task) at the same intensity as the trial to evaluate muscle recovery. EMG (Median Frequency, Peak Power, Peak Power Frequency, Total Power and Zero-crossing Rate) and cardiovascular variables did not demonstrate any statistical difference between the 5-second contractions (p > 0.05) performed before and after the fatiguing task, showing a quick EMG recovery. However, the data analysis showed that the perceived effort variable had not recovered even 10 minutes after the fatigue contraction (p < 0.05). Our results represent a data basis for future comparisons and since subjective felling can affect performance, this study shows the importance of its analysis, since the subjective effort rate was not fully recovered after 10 minutes the end of the exhaustion contraction.

Two-Feature Voiced/Unvoiced Classifier Using Wavelet Transform

This paper proposes a new wavelet-based algorithm for voice/unvoiced classification of speech segments. The classification process is based on: 1) statistical analysis of the energy-frequency distribution of the speech signal using wavelet transform, and 2) estimation of the short-time zero-crossing rate of the signal. First, the ratio of the average energy in the low-frequency wavelet subbands to that of highest-frequency wavelet subband is computed for each time segment of the pre-emphasised speech using a 4-level dyadic wavelet transform, and compared to a pre-determined threshold. This is followed by measuring the zero- crossing rate of the segment and comparing it to a threshold determined by a continually up-dated value of the median of the zero-crossing rates of the speech signal. An experimentally verified criterion based on the re- sults of the above two comparison processes is then applied to obtain the classification decision. The perform- ance of the algorithm has been evaluated on speech data taken from the TIMIT database, and is shown to yield high classification accuracy and robustness to additive noise. technique for V/UV speech classification using two features of the speech signal: (a) the frequency distribution of the average energy and (b) zero-crossing rate, for each speech segment. The performance of the proposed technique has been evaluated using a large database of both clean speech and speech degraded with additive noise. Following this introduction, the second Section gives an overview of the discrete wavelet transform (DWT). The de- tailed description of the proposed V/UV classification algo- rithm is given next. In the forth Section, the various experi- mental results of the performance evaluation of the algorithm are illustrated and discussed. The article concludes by giving a summary of the proposed algorithm and findings of the evaluation process.

수박 내부결함판정을 위한 휴대형 압전형 장갑 센서시스템

Dynamic excitation and response analysis is an acceptable method to determine some of physical properties of agricultural product for quality evaluation. There is a difference in the internal viscoelasticity between sound and defective fruits due to the difference of geometric structures, thereby showing different vibration characteristics. This study was carried out to develop a portable piezoelectric film-based glove sensor system that can separate internally damaged watermelons from sound ones using an acoustic impulse response technique. Two piezoelectric sensors based on polyvinylidene fluoride (PVDF) films to measure an impact force and vibration response were separately mounted on each glove. Various signal parameters including number of peaks, energy ratio, standard deviation of peak to peak distance, zero-crossing rate, and integral value of peaks were examined to develop a regression-estimated model. When using SMLR (Stepwise Multiple Linear Regression) analysis in SAS, three parameters, i.e., zeros value, number of peaks, and standard deviation of peaks were selected as usable factors with a coefficient of determination () of 0.92 and a standard error of calibration (SEC) of 0.15. In the validation tests using twenty watermelon samples (sound 9, defective 11), the developed model provided good capability showing a classification accuracy of 95%.

A noise reduction technique of speech signal using ICA and spectral analysis

This paper discusses the new method on noise reduction exploiting the combined effects of wavelet decomposition, ICA and spectral analysis on noisy speech. The input noisy speech is wavelet decomposed into two signals. Wavelet entropy is computed based on the modified probability density function for the signal derived from the approximation coefficients during wavelet decomposition. By proper entropy comparison, the starting frame is detected. Between the two signals obtained from the wavelet decomposition, one is speech combined with noise and another one is noise alone. These two signals are analysed in independent component analysis (ICA) domain, in order to generate an enhanced speech. Zero-crossing rate is computed and used to discriminate between speech and noise. Then, spectral analysis is performed on the noise prior to starting frame and noisy speech. Elimination of noise frequencies in the noisy speech leads to noise reduced speech. Subjective analysis and experimental results show the considerable noise reduction capability of the proposed algorithm.

Speech detection in noisy environments by wavelet energy-based recurrent neural fuzzy network

This paper proposes a new speech detection method by recurrent neural fuzzy network in variable noise-level environments. The detection method uses wavelet energy (WE) and zero crossing rate (ZCR) as detection parameters. The WE is a new and robust parameter, and is derived using wavelet transformation. It can reduce the influences of different types of noise at different levels. With the inclusion of ZCR, we can robustly and effectively detect speech from noise with only two parameters. For detector design, a singleton-type recurrent fuzzy neural network (SRNFN) is proposed. The SRNFN is constructed by recurrent fuzzy if-then rules with fuzzy singletons in the consequences, and the recurrent property makes them suitable for processing speech patterns with temporal characteristics. The learning ability of SRNFN helps avoid the need of empirically determining a threshold in normal detection algorithms. Experiments with different types of noises and various signal-to noise ratios (SNRs) are performed. The results show that using the WE and ZCR parameters-based SRNFN, a pretty good performance is achieved. Comparisons with another robust detection method, the refined time–frequency-based method, and other detectors have also verified the performance of the proposed method.

Switching Auxiliary Chains for Speech Recognition

This letter investigates the problem of incorporating auxiliary information, e.g., pitch, zero crossing rate (ZCR), and rate-of-speech (ROS), for speech recognition using dynamic Bayesian networks. In this letter, we propose switching auxiliary chains for exploiting different auxiliary information tailored to different phonetic states. The switching function can be specified by a priori knowledge or, more flexibly, be learned from data with information-theoretic dependency selection. Experiments on the OGI Numbers database show that the new model achieves 7% word-error-rate relative reduction by jointly exploiting pitch, ZCR, and ROS, while keeping almost the same parameter size as the standard HMM.

다탄성 Insole의 Workload 감소 효과에 관한 연구

The Work-Related Musculoskeletal Disorders (WMSDs) can be occurred by various factors such as repetition, forceful exertions and awkward postures. Especially, occurrences of the WMSDs on the waist and lower limb are reported in workplaces, demanded standing postures for a long time, in service and manufacturing industry. The static and standing postures without movement for a long time increase work loads to the lower limb and the waist. Accordingly, anti-fatigue mat or anti-fatigue insole is used as a preventing device of the WMSDs. However anti-fatigue mats are limited in space and movement. In this study, multi-elastic insoles are designed and shown the effects of the workload reduction for a long time under the standing work. The foot pressures and EMG (Electromyography) are measured at 0 hour and after 2 hours by 6 health students in their twenties. The 6 prototype insoles are designed with three elastic (Low, Medium and High). These insoles are compared with no insole (insole type 7) as control group. The EMG measurement was conducted to waist (erector spinae muscle), thigh (vastus lateralis muscle) and calf (gastrocnemius muscle). The foot pressure is analyzed by mean pressure value and the EMG analysis is investigated through MF (Median Frequency), MPF (Mean Power Frequency) and ZCR (Zero Crossing Rate). The results of the foot pressure show that the multi-elastic insoles had smaller foot pressure value than that of no-insole. Moreover, Insole 2 and Insole 3 have the smallest increasing rate in foot pressure. The EMG results show that the multi-elastic insoles had smaller EMG shift value than that of no-insole in 2 hour, and then shift value shows the smallest value in Insole 2. Therefore, this study presents that the multi-elastic insoles have reducing effects of the work load for a long time standing work in both side of foot pressure and EMG.

A Model-Based Approach to Constructing Music Similarity Functions

Several authors have presented systems that estimate the audio similarity of two pieces of music through the calculation of a distance metric, such as the Euclidean distance, between spectral features calculated from the audio, related to the timbre or pitch of the signal. These features can be augmented with other, temporally or rhythmically based features such as zero-crossing rates, beat histograms, or fluctuation patterns to form a more well-rounded music similarity function. It is our contention that perceptual or cultural labels, such as the genre, style, or emotion of the music, are also very important features in the perception of music. These labels help to define complex regions of similarity within the available feature spaces. We demonstrate a machine-learning-based approach to the construction of a similarity metric, which uses this contextual information to project the calculated features into an intermediate space where a music similarity function that incorporates some of the cultural information may be calculated.

Event detection in an audio-based sensor network

In this article we set out to examine whether analysis of the audio from a multimedia surveillance application can be used to augment an event detection system based on visual processing, and possibly contribute to any improvements. In processing audio information we are not concerned with identifying or classifying what type of event is detected as our aim is to keep audio processing to a minimum in order to allow deployment on a wireless sensor network. We describe an experiment where we gathered information from a series of traditional wired microphones installed in a typical surveillance setting. We also obtained information on activities carried out from cameras located in the same area. We present the results of analysis of audio information based on the mean of the volume, the zero-crossing rate, and the frequency and how these correlate with events detected visually. We found that detecting events, based on their volume only, returned satisfactory results. We show the results determined by applying this volume based approach to a range of physical environments.

Advances in unsupervised audio classification and segmentation for the broadcast news and NGSW corpora

The problem of unsupervised audio classification and segmentation continues to be a challenging research problem which significantly impacts automatic speech recognition (ASR) and spoken document retrieval (SDR) performance. This paper addresses novel advances in 1) audio classification for speech recognition and 2) audio segmentation for unsupervised multispeaker change detection. A new algorithm is proposed for audio classification, which is based on weighted GMM Networks (WGN). Two new extended-time features: variance of the spectrum flux (VSF) and variance of the zero-crossing rate (VZCR) are used to preclassify the audio and supply weights to the output probabilities of the GMM networks. The classification is then implemented using weighted GMM networks. Since historically there have been no features specifically designed for audio segmentation, we evaluate 16 potential features including three new proposed features: perceptual minimum variance distortionless response (PMVDR), smoothed zero-crossing rate (SZCR), and filterbank log energy coefficients (FBLC) in 14 noisy environments to determine the best robust features on the average across these conditions. Next, a new distance metric, T/sup 2/-mean, is proposed which is intended to improve segmentation for short segment turns (i.e., 1-5 s). A new false alarm compensation procedure is implemented, which can compensate the false alarm rate significantly with little cost to the miss rate. Evaluations on a standard data set-Defense Advanced Research Projects Agency (DARPA) Hub4 Broadcast News 1997 evaluation data-show that the WGN classification algorithm achieves over a 50% improvement versus the GMM network baseline algorithm, and the proposed compound segmentation algorithm achieves 23%-10% improvement in all metrics versus the baseline Mel-frequency cepstral coefficients (MFCC) and traditional Bayesian information criterion (BIC) algorithm. The new classification and segmentation algorithms also obtain very satisfactory results on the more diverse and challenging National Gallery of the Spoken Word (NGSW) corpus.

Speech and Music Classification and Separation: A Review

The classification and separation of speech and music signals have attracted attention by many researchers. The purpose of the classification process is needed to build two different libraries: speech library and music library, from a stream of sounds. However, the separation process is needed in a cocktail-party problem to separate speech from music and remove the undesired one. In this paper, a review of the existing classification and separation algorithms is presented and discussed. The classification algorithms will be divided into three categories: time-domain, frequency-domain, and time-frequency domain approaches. The time-domain approaches used in literature are: the zero-crossing rate (ZCR), the short-time energy (STE), the ZCR and the STE with positive derivative, with some of their modified versions, the variance of the roll-off, and the neural networks. The frequency-domain approaches are mainly based on: spectral centroid, variance of the spectral centroid, spectral flux, variance of the spectral flux, roll-off of the spectrum, cepstral residual, and the delta pitch. The time-frequency domain approaches have not been yet tested thoroughly in literature; so, the spectrogram and the evolutionary spectrum will be introduced. Also, some new algorithms dealing with music and speech separation and segregation processes will be presented.

An improved 2.4kb/s Mixed Excitation Linear Prediction vocoder

This letter presents two improvements on 2.4 kb/s Mixed-Excitation Linear Prediction (MELP) vocoder. The one is a new parameter R edzc named energy to differential zero-crossing rate which is used in adaptation of V/UV decision of transitional segments and low energy level speech segments. The other is a multi-path searching method for Multi-Stage Vector Quantization (MSVQ) of line spectral frequency. Subjective tests show that the intelligiblity and naturallity of improved MELP vocoder are preferable to those of the original one.

Parsimonious Correlated Nonstationary Models for Real Baseband UWB Data

Few ultrawide-band (UWB) models directly fit original baseband UWB data to simultaneously account for their correlation structure, non-Gaussianity, and nonstationarity. The difficulty arises from the fact that no relevant result is available, even in multivariate statistical analysis. It also arises from the attempt to pursue the details of the mechanism that is imagined to be responsible for the generation of UWB data. The consequence is the modeling complexity, which makes it difficult to handle the received signal correlation on the basis of a single realization. Accordingly, various partial characterization is used in the literature instead by virtue of second-order statistics (such as power delay profile), nonparametric characteristics (such as zero-crossing rate), or their combination. In this paper, we take a different philosophy, which believes that the information in the received UWB data itself, as long as fully exploited, plus some simple physical intuition should suffice for the model identification and its parameter estimation. A received UWB signal is decomposed into three factor processes and each is parsimoniously parameterized. The application of the new model to data regeneration and receiver design is illustrated by using the real UWB data acquired by Intel and the TimeDomain Corporation.

Acoustic intruder detection system for home security

This paper propose a new algorithm to detect the intruder in room. The basic idea of the proposed method is to estimate the variation of features of the room acoustic transfer function (RTF). The room transfer function is computed by cross-correlation method. There are some methods to measure the RFT. For example there are the image methods, ray tracing method to measure actually the RFT. In this we estimated RTF using white Gaussian noise that is broadband signal. It is important to extract feature vectors. Feature extraction is the process of computing a numerical representation. We used various features to detect intruder. The features based on the short time Fourier transform (STFT) and the zero-crossing rates were used. Several simulations and actually tests show that the proposed method provides good performance for intruder detection.

The sensitivity of autoregressive model coefficient in quantification of trunk muscle fatigue during a sustained isometric contraction

The goal of the study is to investigate the performance of the first autoregressive model coefficient (ARC) in quantification of fatigue of the trunk muscle. Other parameters such as root mean square (RMS), zero crossing rate (ZCR), mean power frequency (MPF), median frequency (MF) were computed and used for comparison with ARC in this study using slope and coefficient of determination of linear regression model fitted to the normalized parameter values in the time domain in order to assess sensitivity and reliability. Ten males were utilized and electromyographic (EMG) signals were collected at L3/L4 levels of both right and left erector spinae muscles continuously for a period of 20 s while subjects were isometrically extending their trunk at five different force levels: 15%, 30%, 45%, 60%, and 75% of maximal voluntary contraction (MVC). RMS was found to be the worst parameter, ARC was the most sensitive at 15–45% MVC and reliable at 15–60% MVC, and ZCR was more sensitive at 60–75% MVC but less reliable. The fourth order of the autoregressive (AR) model in 0.5 s intervals was validated for EMG signals and ARC may become an potential parameter to describe the trunk fatigue during both static and dynamic exertions. Relevance to industry The first coefficient of autoregressive model can be used as an potential measure to assess the muscle fatigue caused by a prolonged static working posture. Its relatively sensitive fatigue-detecting nature may assist ergonomists in preventing workers from injuries due to cumulative muscle fatigue even at relatively lower force levels.

Non-contact ultrasonic inspection of medical catheters for polymeric bond defects

A non-contact, laser-optic based laser ultrasonic technique referred to as the thermo-acousto-photonic non-destructive evaluation (TAP-NDE) was employed to investigate bond integrity and localized stiffening due to an attached wire stent on small diameter polymeric catheters. Laser-generated interrogating ultrasonic dispersive waves in the catheter were acquired using a fiber-tip interferometer (FTI) running on a HeNe laser. The basic notions of zero-crossing rate and artificial neural network (ANN) were applied to digitized tubular guided-waves to uniquely identify each of the following three bond defects: tensile pull, needle puncture, and crease. These induced flaws represent possible manufacturing defects such as de-bond, potential leak sources, and geometry irregularities. Zero-crossing rates were also found to uniquely identify localized stiffening due to an attached wire stent proving that this technique can unambiguously identify propagation modes from among non-propagation modes or vibrations. The 100% success rate reported in the paper renders the utility of TAP-NDE, along with ANN based classification scheme using zero-crossing rates, a viable quantitative measure for inspecting small-diameter polymeric medical tubing for sub-mm defects in real-time.

Nonlinear signal classification using geometric statistical features in state space

A new methodology in the framework of high-dimensional shape analysis in state space is proposed for nonlinear signal classification. The zero-crossing rate on a Poincare surface of a section is used as a feature. Experiments regarding oceanic signal classification show that the proposed methodology can provide some information not contained in spectra.

A Three-Level Speech, Music, and Mixture Classifier

Due to the new techniques of analysis and synthesis of speech signals, the musical signal processing has gained particular weight, and therefore, the classical sound analysis techniques are used in processing music signals. In this paper, a general three-level algorithm for discriminating three general types of signals: speech, music, and mixture of both signals is proposed. The proposed classifier is based on the well-known zero-crossing rate (ZCR) [1] and short-time energy (STE) [2,3] algorithms, with the positive derivative and voting procedures. Some theoretical analysis and simulation has been applied to a library of different types of musical and speech signals to show the performance of the proposed algorithm.

Zero-crossing rates of wavelet frame representations for texture classification

The zero-crossing rates (ZCRs) of the wavelet frame representation of texture images are proposed as features for texture classification. Results indicate that ZCR features lower the probability of error (PE) by 40% over energy (EN) and correlation coefficient features. Augmenting ZCR features with EN features improves the PE by 70% over ZCR features alone.