Short-time Energy Research Articles

Automatic Detection of Shadda in Modern Standard Arabic Continuous Speech

The presence of diacritics Shadda in Arabic continuous speech may lead to the reduction of the accuracy of automatic Word Boundary Detection (WBD), which caused one word will be wrongly detected as two words. Therefore, this will affect the accuracy of Automatic Speech Recognition (ASR), if it is based on WBD. Shadda is one of the essential characteristics of the Arabic language which represents a consonant doubling. In this paper, a proposed method of automatic detection of Shadda in Modern Standard Arabic (MSA) continuous speech was introduced to improve the accuracy of WBD in MSA continuous speech. The prosodic features namely Short Time Energy (STE), Fundamental Frequency and Intensity were investigated for its ability as Shadda pattern detection in continuous MSA speech. We have analyzed the proposed features by implementing a separated algorithm for each feature to detect Shadda pattern automatically. In addition, a new proposed method which is a combination of STE and Intensity were introduced. The dataset in this work is a collection of 1-hour TV broadcast news from Aljazeera Arabic TV channel for 2018 - broadcasters. We found that the Shadda pattern is very similar to unvoiced regions of speech, and this represents a big challenge for the improvement of WDB using Shadda. Results showed that the detection of Shadda using Short Time Energy and Intensity outperforms the Fundamental frequency with 55% of accuracy. Intensity achieved 71.5% in accuracy. In addition, a combination between Intensity & STE features was performed and achieved good results with 67.15% in accuracy. The number of false positive too has been reduced compared to Intensity alone.

Segmentation of continuous audio recordings of Carnatic music concerts into items for archival

Concert recordings of Carnatic music are often continuous and unsegmented. At present, these recordings are manually segmented into items for making CDs. The objective of this paper is to develop algorithms that segment continuous concert recordings into items using applause as a cue. Owing to the ‘here and now’ nature of applauses, the number of applauses exceeds the number of items in the concert. This results in a concert being fragmented into different segments. In the first part of the paper, applause locations are identified using time, and spectral domain features, namely, short-time energy, zero-crossing rate, spectral flux and spectral entropy. In the second part, inter-applause segments are merged if they belong to the same item. The main component of every item in a concert is a composition. A composition is characterised by an ensemble of vocal (or main instrument), violin (optional) and percussion. Inter-applause segments are classified into three segments, namely, vocal solo, violin solo, composition and thaniavarthanam using tonic normalised cent filter-bank cepstral coefficients. Adjacent composition segments are merged into a single item, if they belong to the same melody. Meta-data corresponding to the concert in terms of items, available from listeners, are matched to the segmented audio. The applauses are further classified based on strength using Cumulative Sum. The location of the top three highlights of every concert is documented. The performance of the proposed approaches to applause identification, inter-applause classification and mapping of items is evaluated on 50 live recordings of Carnatic music concerts. The applause identification accuracy is 99%, and the inter- and intra-item classification is 93%, while the mapping accuracy is 95%.

A novel hand gesture recognition method based on 2-channel sEMG.

Hand gesture recognition is getting more and more important in the area of rehabilitation and human machine interface (HMI). However, most current approaches are difficult to achieve practical application because of an excess of sensors. In this work, we proposed a method to recognize six common hand gestures and establish the optimal relationship between hand gesture and muscle by utilizing only two channels of surface electromyography (sEMG). We proposed an integrated approach to process the sEMG data including filtering, endpoint detection, feature extraction, and classifier. In this study, we used one-order digital lowpass infinite impulse response (IIR) filter with the cutoff frequency of 500 Hz to extract the envelope of the sEMG signals. The energy was utilized as a feature to detect the endpoint of motion. The short-time energy, zero-crossing rate and linear predictive coefficient (LPC) with 12 levels were chosen as the features and back propagation (BP) neural network was utilized to classify. In order to test the method, five subjects were involved in the experiment to test the hypothesis. With the proposed method, 96.41% to 99.70% recognition rate was obtained. The experimental results revealed that the proposed method is highly efficient both in sEMG data acquisition and hand motions recognition, and played a role in promoting hand rehabilitation and HMI.

Automatic syllabification of speech signal using short time energy and vowel onset points

This paper describes a language independent method for automatic syllabification of speech signal. This method utilizes the valleys in short time energy (STE) contour and location of vowel onset points (VOP) for marking the syllable boundaries. In the proposed method, automatic syllabification is performed in three steps. First, long silence/pause regions are marked with the help of speech/non-speech detection. Then VOPs are located from the Hilbert Envelope of LP residual. The existence of more than one VOP in a continuous speech region (identified using speech/non-speech detection in the first step) is an indication of syllable boundaries within the region. Location with minimum energy in the STE contour between two consecutive VOP is identified as the syllable boundary. Since automatic VOP detection algorithm fails to detect some of the VOPs, certain syllable boundaries will be missed. Therefore, at the third step, additional syllable boundaries are detected from STE contour by fixing a valley threshold which is equal to the mean value of STE corresponding to each speech region between two consecutive syllable boundaries. This method is evaluated for 50 sentences each in read, extempore and conversational mode speech of Malayalam and Bengali languages. Overall accuracy of 80% is obtained with ± 50 ms tolerance with reference to manually marked syllable boundaries for this database. Method also shows good accuracy in case of TIMIT and NTIMIT data without tuning of thresholds and other parameters. This method is useful for applications that do not require exact syllable boundaries, rather a meaningful separation of syllables. Application of this technique for prosody based emotion recognition is illustrated using Emo-DB German emotional database.

An Intelligent Monitoring Network for Detection of Cracks in Anvils of High-Press Apparatus.

Due to the endurance of alternating high pressure and temperature, the carbide anvils of the high-press apparatus, which are widely used in the synthetic diamond industry, are prone to crack. In this paper, an acoustic method is used to monitor the crack events, and the intelligent monitoring network is proposed to classify the sound samples. The pulse sound signals produced by such cracking are first extracted based on a short-time energy threshold. Then, the signals are processed with the proposed intelligent monitoring network to identify the operation condition of the anvil of the high-pressure apparatus. The monitoring network is an improved convolutional neural network that solves the problems that may occur in practice. The length of pulse sound excited by the crack growth is variable, so a spatial pyramid pooling layer is adopted to solve the variable-length input problem. An adaptive weighted algorithm for loss function is proposed in this method to handle the class imbalance problem. The good performance regarding the accuracy and balance of the proposed intelligent monitoring network is validated through the experiments finally.

New magnetic aluminum matrix composites (Al-Zn-Si) reinforced with nano magnetic Fe3O4 for aeronautical applications

Aluminum metal matrix composites (AMMCs) are light-weight materials are widely used in structural applications due to their favorable properties such as lightweight, high specific strength and modulus, wear resistance and low coefficient of thermal expansion. Today, new developed magnetic aluminium based composites (Al-Zn-Si) became very attractive due to their improved magnetic, physical and mechanical properties. These composites, depending on final desired properties with different reinforcement types, are very suitable for electrical motors and other usage in aircraft engineering. These promising properties of AMMCs are attributed to the size and distribution of the reinforcement, as well as to the grain size of the matrix. Process that was used in this work is called ‘Sinter-Forging’ during which compacted aluminium specimens were forged just after sintering. A novel near-net shape, low-cost sinter-forging approach to processing particle-reinforced metal matrix composites allow manufacturing parts for high performance applications with short processing time and low energy consumption. The aim of this work is to briefly present the efficient ‘Sinter-Forging Process’ and to summarize properties of new composites developed for aeronautical applications.

WiStep

Inspired by the emerging WiFi-based applications, in this paper, we leverage ubiquitous WiFi signals and propose a device-free step counting system, called WiStep. Based on the multipath propagation model, when a person is walking, her torso and limbs move at different speeds, which modulates wireless signals to the propagation paths with different lengths and thus introduces different frequency components into the received Channel State Information (CSI). To count walking steps, we first utilize time-frequency analysis techniques to segment and recognize the walking movement, and then dynamically select the sensitive subcarriers with largest amplitude variances from multiple CSI streams. Wavelet decomposition is applied to extract the detail coefficients corresponding to the frequencies induced by feet or legs, and compress the data so as to improve computing speed. Short-time energy of the coefficients is then calculated as the metric for step counting. Finally, we combine the results derived from the selected subcarriers to produce a reliable step count estimation. In contrast to counting steps based on the torso frequency analysis, WiStep can count the steps of in-place walking even when the person's torso speed is null. We implement WiStep on commodity WiFi devices in two different indoor scenarios, and various influence factors are taken into consideration when evaluating the performance of WiStep. The experimental results demonstrate that WiStep can realize overall step counting accuracies of 90.2% and 87.59% respectively in these two scenarios, and it is resilient to the change of scenarios.

Acceptance and Classification of Gears Based on Sound Signals Spectrum Analysis

This paper work presents our proposed systematic approach in solving the industrial problem on identifying the good and bad gears by analyzing the spectrum of sound signals produced by the gears; In this proposed approach we treat this problem as a pure machine learning and classification problem having two classes (good gears and bad gears), whereby we have analyzed the spectrum of several sound signal samples from good and bad gears then extracted five audio features from their spectrum (Short time energy, zero crossing rate, Spectral entropy, pitch and block energy entropy) which after investigation, we found a significant difference between the two classes. We formed a 5D features vector; we used 10 features vectors from good gears and 10 from bad gears as our training samples for finding the discriminating point. After features extraction, we apply Support Vector Machine (SVM) learning classification method to classify the new features vector extracted from the unknown sound from the gear.

Ischemic Stroke Detection System with Computer Aided Diagnostic Capability

Ischemic stroke is caused by an occurrence of emboli which travels along the blood vessel in cerebral arteries that eventually trapped near the vessel wall and become stenosis. Transcranial Doppler (TCD) Ultrasound has been used as tool for manual detection of emboli, but the monitoring process is time-consuming and it requires human expert to perform the task. Due to the limited number of experts, this makes manual emboli detection becomes a challenging task. Recently, many researches has devoted to the development of automated emboli detection. In this paper, we investigate the use of frequency and time domain calculations to automatically detect the emboli. In the first method, sinusoidal modelling (SM) is employed to inspect the spectrum of high magnitude frequency component. The second method uses the energy and zero crossing rate (E+ZCR) method. While, the third method is short time energy and short time average zero crossing rate (STE+STAZCR). The experimental results reveal that the sinusoidal modelling gives the best results with genuine acceptance rate is achieved at 84.2%. However, this study also exposes that each approach has its own advantage hence this investigation spurs many rooms of future investigation.

Novel Computing Method for Short Programming Time and Low Energy Consumption in HfO2 Based RRAM Arrays

This paper proposes a novel technique for reducing programming time and energy consumption in resistive random access memory (RRAM) arrays based on ramped voltage stress (RVS). RVS method is correlated to conventional constant voltage stress method (CVS) using an analytical model validating RVS as a reliable technique for switching time characterization in RRAM arrays. RVS method is optimized to reduce programming time and energy consumption providing a quantitative and qualitative link between programming method and tails improvement in memory arrays. Switching time distribution is much more controlled: half a decade using optimized RVS in comparison with ~3 decades distribution using conventional CVS method. Energy consumption is reduced by 4 orders of magnitude at $+5\sigma $ quantiles using our proposed technique compared to CVS.

Application of modified microwave polyol process method on NiMo/C nanoparticle catalyst preparation for hydrogenated biodiesel production

The development of renewable feedstock-based diesel fuel is start to come up as the solution of national energy problem. However, the thermal and oxidative stability of biodiesel is not good enough. As a result, biodiesel can only be added to commercial diesel fuel as a mixture with concentration under 20%. To get better thermal and oxidation stability, partial hydrogenation process is applied to biodiesel caused the increase of monounsaturated FAME structure. Activated carbon supported NiMo nanocrystal catalyst was used in partial hydrogenation reaction to get high activity, conversion, and selectivity. In this research, NiMo/C catalyst was prepared by modified microwave polyol process method, which is provided a rapid heating and cooling process. This method can produce nano-sized NiMo/C catalyst with short time and low energy consumption. NiMo/C catalyst produced in this research has 285.85 m2/gram surface area and 77.79 nm crystal size, resulting 20.41% conversion and 8.87% selectivity of biodiesel product. Further research should be conducted to obtain optimum condition.

An efficient speech perceptual hashing authentication algorithm based on DWT and symmetric ternary string

According to the situation that speech perceptual hashing methods are not appropriated for real-time speech content authentication in mobile computing environment, a novel DWT-based perceptual hashing algorithm, which uses a combination of time-domain and frequency-domain features, was proposed to protect the speech data in the cloud. Firstly, by discrete wavelet transform (DWT), a new signal in frequency-domain is generated from the original speech signal after pre-processing and intensity-loudness transform (ILT). Secondly, coefficients of low frequency wavelet decomposition are partitioned into equal-sized and non-overlapping blocks, and logarithmic short-time energy of each block is computed to obtain speech signals features in frequency-domain. Finally, combined with spectral flux features (SFF) of speech signal in time-domain, a ternary perceptual hashing sequence is created. Experiment results illustrate that ternary form is better to stand for hash digest than binary form, the proposed algorithm has a good robustness against content preserving operations, discrimination, good compaction and high efficiency, and detects the tamper localisation as well.

Research on depression detection algorithm combine acoustic rhythm with sparse face recognition

Due to the existence of false positive rate of the traditional depression diagnosis method, this paper proposes a multi-modal fusion algorithm based on speech signal and facial image sequence for depression diagnosis. Introduced spectrum subtraction to enhance depressed speech signal, and use cepstrum method to extract pitch frequency features with large variation rate and formant features with significant difference, the short time energy and Mel-frequency cepstral coefficients characteristic parameters for different emotion speeches are analyzed in both time domain and frequency domain, and establish a model for training and identification. Meanwhile, this paper implements the orthogonal match pursuit algorithm to obtain a sparse linear combination of face test samples, and cascade with voice and facial emotions based proportion. The experimental results show that the recognition rate based on the depression detection algorithm of fusion speech and facial emotions has reached 81.14%. Compared to the existing doctor’s accuracy rate of 47.3%, the accuracy can bring extra 71.54% improvement by combining with the proposed method of this paper. Additionally, it can easily apply to the hardware and software on the existing hospital instruments with low cost. Therefore, it is an accurate and effective method for diagnosing depression.

Monitoring the quality of welding based on welding current and ste analysis

Qualities of welding play an important part in industry especially in manufacturing field. Post-welding non-destructive test is one of the importance process to ensure the quality of welding but it is time consuming and costly. To reduce the chance of defects, online monitoring had been utilized by continuously sense some of welding parameters and predict welding quality. One of the parameters is welding current, which is rich of information but lack of study focus on extract them at signal analysis level. This paper presents the analysis of welding current using Short Time Energy (STE) signal processing to quantify the pattern of the current. GMAW set with carbon steel specimens are used in this experimental study with high-bandwidth and high sampling rate oscilloscope capturing the welding current. The results indicate welding current as signatures have high correlation with the welding process. Continue with STE analysis, the value below 5000 is declare as good welding, meanwhile the STE value more than 6000 is contained defect.

Pitch segmentation of speech signals based on short-time energy waveform

In general, speech is constituted of quasi-repetitive patterns called pitches representing the speech fundamental period and tonal information of the voice. Extraction of pitch information that is crucial for many speech processing techniques, usually faces a noise problem and interference caused by high-order harmonic components. This paper introduces a novel, noise-robust method for determining speech fundamental frequency and pitch segmentation, based on a short-time energy waveform (SEW), defined as a moving average squared signal. When applying a moving average filter with a window size closed to the fundamental period, nearly repetitive patterns, with fewer ripples, synchronizing with actual pitches can clearly be observed in the SEW. The DC component in the SEW is removed using morphological top-hat and bottom-hat transforms. The fundamental frequency is determined as the frequency corresponding to the largest peak of the power spectrum of the DC-removed SEW. Finally, a time-domain window search is then performed to locate local extrema associated with pitches. Compared to traditional pitch detection techniques, the proposed technique yields pitch segmentation results with a higher rate of accuracy and greater noise robustness.

Frog sound identification using extended k-nearest neighbor classifier

Frog sound identification based on the vocalization becomes important for biological research and environmental monitoring. As a result, different types of feature extractions and classifiers have been employed to evaluate the accuracy of frog sound identification. This paper presents a frog sound identification with Extended k-Nearest Neighbor (EKNN) classifier. The EKNN classifier integrates the nearest neighbors and mutual sharing of neighborhood concepts, with the aims of improving the classification performance. It makes a prediction based on who are the nearest neighbors of the testing sample and who consider the testing sample as their nearest neighbors. In order to evaluate the classification performance in frog sound identification, the EKNN classifier is compared with competing classifier, k -Nearest Neighbor (KNN), Fuzzy k -Nearest Neighbor (FKNN) k - General Nearest Neighbor (KGNN)and Mutual k -Nearest Neighbor (MKNN) on the recorded sounds of 15 frog species obtained in Malaysia forest. The recorded sounds have been segmented using Short Time Energy and Short Time Average Zero Crossing Rate (STE+STAZCR), sinusoidal modeling (SM), manual and the combination of Energy (E) and Zero Crossing Rate (ZCR) (E+ZCR) while the features are extracted by Mel Frequency Cepstrum Coefficient (MFCC). The experimental results have shown that the EKNCN classifier exhibits the best performance in terms of accuracy compared to the competing classifiers, KNN, FKNN, GKNN and MKNN for all cases.

Synchrony-Based Feature Extraction for Robust Automatic Speech Recognition

This letter discusses the application of models of temporal patterns of auditory-nerve firings to enhance robustness of automatic speech recognition systems. Most conventional feature extraction schemes (such as mel-frequency cepstral coefficients and perceptual linear processing coefficients) are based on short-time energy in each frequency band, and the temporal patterns of auditory-nerve activity are discarded. We compare the impact on speech recognition accuracy of several types of feature extraction schemes based on the putative synchrony of auditory-nerve activity, including feature extraction based on a modified version of the generalized synchrony detector proposed by Seneff, and a modified version of the averaged localized synchrony response proposed by Young and Sachs. It was found that the use of features based on auditory-nerve synchrony can indeed improve speech recognition accuracy in the presence of additive noise based on experiments using multiple standard speech databases. Recognition accuracy obtained using the synchrony-based features is further increased if some form of noise removal is applied to the signal before the synchrony measure is estimated. Signal processing for noise removal based on the noise suppression that is a part of PNCC feature extraction is more effective toward this end than conventional spectral subtraction.

A complementary approach for fault diagnosis of rolling bearing using canonical variate analysis based short-time energy feature

Signal decomposition is a meaningful and effective methodology which is widely used for fault diagnosis. Mode/feature selection is an inevitable topic for fault diagnosis of rolling bearing due to over-decomposition. In practical application, the selection of sensitive modes is a challenging task, so many valuable works have been performed to cope with it. However, the published works lack an effective approach to acquire few meaningful modes by avoiding the complicated mode selection procedures, prior to feature extraction. Moreover, selection of the modes of interest fails to take the residual part into account, which makes the diagnosis result sensitive to the number of modes/features retained. This paper proposes a complementary approach to extract fault features and avoid the selection of single mode of interest, which employs canonical variate analysis to convert the original variable into two complementary spaces; canonical variate space; and residual space. Then the complementary statistical indicators Hotelling T2 statistic and Q statistic are used to provide important information about the conditions of the rolling bearing. Subsequently, a new feature index, complementary short-time energy extracted from the two statistics are used as fault features which are given as an input to a classifier such as a support vector machine. Two data sets collected from different test rigs are used for demonstration of the proposed work. The experimental result shows that the troublesome feature/mode selection issue is avoided, and the diagnosis result is not sensitive to the number of canonical variate retained. Besides, the proposed approach can identify various working conditions of rolling bearing accurately, which is simple and effective for fault diagnosis of rolling bearing, compared with the existing methods.

의료 정보 FHIR 리소스 무선 데이터 방송을 위한 분산 인덱싱 기법

차세대 의료 정보 교환 표준인 FHIR는 빠른 의료정보 교환이 가능할 뿐 아니라 효과적인 다양한 의료서비스가 가능하다. 본 논문은 FHIR 리소스를 보안 채널기반의 무선 데이터 방송에 적용하여 사용자에게 효율적으로 리소스를 전달할 수 있도록 하기 위해 FHIR 리소스 기반의 인덱싱 기법을 제안한다. 제안된 인덱싱 기법은 리소스를 받고자 하는 사용자 정보와 사용자에 대한 FHIR 리소스를 유지하여 대량의 사용자가 빠른 시간에 적은 에너지를 사용하여 원하는 리소스를 다운로드할 수 있도록 한다. 시뮬레이션을 통해 제안된 인덱싱 기법이 다른 기법들 보다 우수한 성능을 보임을 보였다. FHIR, next-generation standard for health information exchange, allows to exchange health information fast and to provide various health services. In this paper, we propose an indexing scheme of FHIR resources for adopting the resources to wireless data broadcasting with a secure channel. That scheme keeps the information of users to support to download FHIR resources from the secure wireless broadcast channel and the information on the resources. Using the proposed index, massive users can download their desired FHIR resources with less energy in short time. With simulation studies, we show the proposed indexing scheme outperforms other scheme broadcasting FHIR resources.

Protection Strategy of Islanded Micro-Grid Based on Short-Time Energy Segment

Protection Strategy of Islanded Micro-Grid Based on Short-Time Energy Segment