Short-term Features Research Articles

Unveiling hidden migration and mobility patterns in climate stressed regions: A longitudinal study of six million anonymous mobile phone users in Bangladesh

Climate change is likely to drive migration from environmentally stressed areas. However quantifying short and long-term movements across large areas is challenging due to difficulties in the collection of highly spatially and temporally resolved human mobility data. In this study we use two datasets of individual mobility trajectories from six million de-identified mobile phone users in Bangladesh over three months and two years respectively. Using data collected during Cyclone Mahasen, which struck Bangladesh in May 2013, we show first how analyses based on mobile network data can describe important short-term features (hours–weeks) of human mobility during and after extreme weather events, which are extremely hard to quantify using standard survey based research. We then demonstrate how mobile data for the first time allow us to study the relationship between fundamental parameters of migration patterns on a national scale. We concurrently quantify incidence, direction, duration and seasonality of migration episodes in Bangladesh. While we show that changes in the incidence of migration episodes are highly correlated with changes in the duration of migration episodes, the correlation between in- and out-migration between areas is unexpectedly weak. The methodological framework described here provides an important addition to current methods in studies of human migration and climate change.

Local spectral variability features for speaker verification

Speaker verification techniques neglect the short-time variation in the feature space even though it contains speaker related attributes. We propose a simple method to capture and characterize this spectral variation through the eigenstructure of the sample covariance matrix. This covariance is computed using sliding window over spectral features. The newly formulated feature vectors representing local spectral variations are used with classical and state-of-the-art speaker recognition systems. Results on multiple speaker recognition evaluation corpora reveal that eigenvectors weighted with their normalized singular values are useful in representing local covariance information. We have also shown that local variability features can be extracted using mel frequency cepstral coefficients (MFCCs) as well as using three recently developed features: frequency domain linear prediction (FDLP), mean Hilbert envelope coefficients (MHECs) and power-normalized cepstral coefficients (PNCCs). Since information conveyed in the proposed feature is complementary to the standard short-term features, we apply different fusion techniques. We observe considerable relative improvements in speaker verification accuracy in combined mode on text-independent (NIST SRE) and text-dependent (RSR2015) speech corpora. We have obtained up to 12.28% relative improvement in speaker recognition accuracy on text-independent corpora. Conversely in experiments on text-dependent corpora, we have achieved up to 40% relative reduction in EER. To sum up, combining local covariance information with the traditional cepstral features holds promise as an additional speaker cue in both text-independent and text-dependent recognition.

The CM4 model prediction of ground variation of the geomagnetic diurnal field away from quiet time

We analyse the geomagnetic diurnal variation for days away from quiet time to see how well the comprehensive model (CM4) can reasonably predict ground variation of the diurnal field. To do this, we compared ground observatory hourly means to predictions given by the CM4 model for days away from quiet time. Our results show that, away from quiet time, the CM4 model is producing more reasonable predictions than expected, despite the lack of active data in the original model dataset. However, the CM4 model is not doing so well predicting short term features during period of rapid variations, especially for the X component of the geomagnetic diurnal variation field. When comparing the different modelled diurnal variation field maps of the CM4 model and the observatory data, our results show that the model to data fitness increases as we increase the spherical harmonic degrees. From our results we could see that the inability of the CM4 model to accurately predict the geomagnetic diurnal field for days away from quiet time, during time of rapid variations, may be due to the fact that the external field descriptions included in the CM4 model could not sufficiently explain the field contributions for days away from quiet time. This is seen in the low coherence, agreement and correlation in the comparison and cross correlation coefficient between the X component of the observatory data and the Dst index (which allows CM4 model to respond to active conditions outside of the original geomagnetic activity remit).

Toward Agile Architecture: Insights from 15 Years of ATAM Data

Agile teams strive to balance short-term feature development with longer-term quality concerns. These evolutionary approaches often hit a complexity wall' from the cumulative effects of unplanned changes, resulting in unreliable, poorly performing software. So, the agile community is refocusing on approaches to address architectural concerns. Researchers analyzed quality attribute concerns from 15 years of Architecture Trade-Off Analysis Method data, gathered from 31 projects. Modifiability was the dominant concern across all project types; performance, availability, and interoperability also received considerable attention. For IT projects, a relatively new quality-deployability-emerged as a key concern. The study results provide insights for agile teams allocating architecture-related tasks to iterations. For example, teams can use these results to create checklists for release planning or retrospectives to help assess whether to address a given quality to support future needs. This article is part of a special issue on Software Architecture.

Discriminative re-ranking for automatic speech recognition by leveraging invariant structures

An invariant structure was proposed in Minematsu (2004) and Minematsu et al. (2010) and it is a long-span feature to suppress non-linguistic factors. In contrast to frame-based features such as Mel-Frequency Cepstrum Coefficients (MFCC), the invariant structures are extracted as contrasts between speech events in a given utterance. Because the invariant structure is not a time series of short-term features, it is difficult to use it directly in the general framework of Automatic Speech Recognition (ASR) although its robustness against non-linguistic factors is desirable for ASR. To introduce the invariant structure effectively to ASR, we are working on a method to leverage the invariant structure in a discriminative re-ranking paradigm for ASR. In our re-ranking paradigm, a baseline ASR system is used to generate N-best lists with hypothesized phoneme-level alignments so that we can extract one invariant structure for each hypothesis. We also propose methods to convert an extracted invariant structure into a fixed-dimensional feature vector to be used in discriminative re-ranking. Experimental results on the three tasks of continuous digit recognition, digit recognition in noisy environments, and large vocabulary continuous speech recognition showed significant error reductions and robustness improvements against noisy environments.

Grading hypoxic–ischemic encephalopathy severity in neonatal EEG using GMM supervectors and the support vector machine

ObjectiveThis work presents a novel automated system to classify the severity of hypoxic–ischemic encephalopathy (HIE) in neonates using EEG. MethodsA cross disciplinary method is applied that uses the sequences of short-term features of EEG to grade an hour long recording. Novel post-processing techniques are proposed based on majority voting and probabilistic methods. The proposed system is validated with one-hour-long EEG recordings from 54 full term neonates. ResultsAn overall accuracy of 87% is achieved. The developed grading system has improved both the accuracy and the confidence/quality of the produced decision. With a new label ‘unknown’ assigned to the recordings with lower confidence levels an accuracy of 96% is attained. ConclusionThe statistical long-term model based features extracted from the sequences of short-term features has improved the overall accuracy of grading the HIE injury in neonatal EEG. SignificanceThe proposed automated HIE grading system can provide significant assistance to healthcare professionals in assessing the severity of HIE. This represents a practical and user friendly implementation which acts as a decision support system in the clinical environment. Its integration with other EEG analysis algorithms may improve neonatal neurocritical care.

IMPROVED SPEAKER-INDEPENDENT EMOTION RECOGNITION FROM SPEECH USING TWO-STAGE FEATURE REDUCTION

In the recent years, researchers are focusing to improve the accuracy of speech emotion recognition. Generally, high emotion recognition accuracies were obtained for two-class emotion recognition, but multi-class emotion recognition is still a challenging task . The main aim of this work is to propose a two-stage feature reduction using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) for improving the accuracy of the speech emotion recognition (ER) system. Short-term speech features were extracted from the emotional speech signals. Experiments were carried out using four different supervised classifi ers with two different emotional speech databases. From the experimental results, it can be inferred that the proposed method provides better accuracies of 87.48% for speaker dependent (SD) and gender dependent (GD) ER experiment, 85.15% for speaker independent (SI) ER experiment, and 87.09% for gender independent (GI) experiment.

Experimentation Using Short-Term Spectral Features for Secure Mobile Internet Voting Authentication

We propose a secure mobile Internet voting architecture based on the Sensus reference architecture and report the experiments carried out using short-term spectral features for realizing the voice biometric based authentication module of the architecture being proposed. The short-term spectral features investigated are Mel-Frequency Cepstral Coefficients (MFCCs), Mel-Frequency Discrete Wavelet Coefficients (MFDWC), Linear Predictive Cepstral Coefficients (LPCC), and Spectral Histogram of Oriented Gradients (SHOGs). The MFCC, MFDWC, and LPCC usually have higher dimensions that oftentimes lead to high computational complexity of the pattern matching algorithms in automatic speaker recognition systems. In this study, higher dimensions of each of the short-term features were reduced to an 81-element feature vector per Speaker using Histogram of Oriented Gradients (HOG) algorithm while neural network ensemble was utilized as the pattern matching algorithm. Out of the four short-term spectral features investigated, the LPCC-HOG gave the best statistical results withRstatistic of 0.9127 and mean square error of 0.0407. These compact LPCC-HOG features are highly promising for implementing the authentication module of the secure mobile Internet voting architecture we are proposing in this paper.

Quasi-static cyclic tests on super-lightweight EPS concrete shear walls

This study introduces a new emerging structural system, called JK system, which uses JK walls as its main structural elements. JK wall, first proposed by Joseph Kiefer, is a kind of shear wall constructed with low-strength/super-lightweight Expanded Polystyrene (EPS) concrete and reinforced by JK panel, JK stiffener and some additional steel rebars. The study experimentally examines behavior of three JK wall specimens with different reinforcement and level of gravity loads under quasi-static cyclic loading. Obtained results indicate that JK walls can sustain large ductility demands accompanied by stable hysteresis loops. All specimens are also numerically investigated in order to obtain a reliable analytical tool. In this paper, it is shown that a low-strength concrete, currently recognized as a nonstructural material, can be used as a structural concrete having a satisfactory behavior. Finally, a seven story building with JK system is considered to numerically study the above claim. However, more studies are still required to fully capture all short and long term features of structural EPS concrete elements.

Visual Saliency Detection: An Information Theoretic Algorithm Combined Long-term with Short-term Features

Visual Saliency Detection: An Information Theoretic Algorithm Combined Long-term with Short-term Features

Non-paraneoplastic Autoantibody-negative Limbic Encephalitis Characterized by Mild Memory Impairment: A Case Report

Encephalitis that primarily involves limbic system structures such as the hippocampus and parahippocampal gyrus has been described in early papers, most commonly characterized by a subacute progressive impairment of short-term memory, psychiatric features and seizures. While these findings might be caused by viral infections or systemic autoimmune disorders, many patients with limbic encephalitis have an immune-mediated etiology (paraneoplastic or not) characterized with serum or CSF antineuronal antibodies. This case reports about non-paraneoplastic autoantibody-negative limbic encephalitis in which there are no detection of antigens and no evidence of tumors. Received: August 22, 2014 Revision received: September 2, 2014 Accepted: September 2, 2014

Music Genre Classification Using Spectral Analysis and Sparse Representation of the Signals

In this paper, we proposed a robust music genre classification method based on a sparse FFT based feature extraction method which extracted with discriminating power of spectral analysis of non-stationary audio signals, and the capability of sparse representation based classifiers. Feature extraction method combines two sets of features namely short-term features (extracted from windowed signals) and long-term features (extracted from combination of extracted short-time features). Experimental results demonstrate that the proposed feature extraction method leads to a sparse representation of audio signals. As a result, a significant reduction in the dimensionality of the signals is achieved. The extracted features are then fed into a sparse representation based classifier (SRC). Our experimental results on the GTZAN database demonstrate that the proposed method outperforms the other state of the art SRC approaches. Moreover, the computational efficiency of the proposed method is better than that of the other Compressive Sampling (CS)-based classifiers.

Novel Long-Term Information Based Language Identification

A novel long-term information feature for language identification called shifted cepstra curve (SCC) is presented in this paper. Long-term information consists of information over multiple frames, which are commonly used in language identification systems. For instance, in parallel phone recognition language model (PPRLM), the feature vector contains not only information surpassing multiple frames but also linguistic knowledge [1]. However high computational cost for modeling linguistic gram may preclude their use in tasks which demand low memory. By contrast, experiments have proved that linguistics independent long-term information can also achieve high performance in language identification with much lower computing cost. For instance, Shifted delta cepstra (SDC) is employed as long-term information features to establish GMM based language identification systems, which can achieve comparative or even superior performance to PPRLM [2-4]. While, though SDC feature could model the dynamical information across multiple frames, the approximation is not precise enough for language identification. Thus, this paper further presents a new method for linguistics independent long-term information extraction by curve fitting algorithm. Experiments show that new feature based language identification systems are superior to not only short-term features based but also SDC features based systems.

Speaker overlap detection with prosodic features for speaker diarisation

The handling of overlapping speech in the context of speaker diarisation attracted in recent years the interest of the scientific community, since speaker overlap was identified as one of the factors degrading the performance of conventional diarisation systems. In this study, the authors are discussing the possibility of using long-term prosodic features for the detection of overlapping speech, which is subsequently employed in speaker diarisation to improve the baseline system. The most relevant subset from the set of candidate prosodic features is determined in two steps. First, a ranking according to minimal-redundancy-maximal-relevance criterion is obtained, and then a hill-climbing wrapper strategy is applied for determining the optimal number of prosodic features, which should accompany short-term spectral features for overlap detection. In experiments on the augmented multi-party interaction (AMI) meeting distant-channel data, the authors show that the addition of prosodic features decreased overlap detection error. Detected overlap segments were used in speaker diarisation to recover missed speech by assigning multiple speaker labels and to increase the purity of speaker clusters. Improvements of the baseline diarisation system are reported in both single- and multi-site data conditions. However, the extension of the diarisation system with TDOAs showed its incompatibility with the overlap exclusion technique.

MFCC and Prosodic Feature Extraction Techniques: A Comparative Study

In this paper our main aim to provide the difference between cepstral and non-cepstral feature extraction techniques. Here we try to cover-up most of the comparative features of Mel Frequency Cepstral Coefficient and prosodic features. In speaker recognition, there are two type of techniques are available for feature extraction: Short-term features i.e. Mel Frequency Cepstral Coefficient (MFCC) and long-term features (Prosodic) extraction techniques. In this paper, we explore the usefulness of prosodic features for syllable classification and MFCC for feature extraction of a speech signal followed by comparison between them. The Me1 Frequency Cepstral Coefficients (MFCC) is one of the most important features extraction techniques, which is required among various kinds of speech applications. The MFCC features are extracted from the speaker phonemes in the presegmented speech sentences. Now days Prosodic features are currently used in most emotion recognition algorithms Prosodic features are relatively simple in their structures and known for their effectiveness in some speech recognition tasks. There are various ways of generating prosodic syllable contour features that have recently been applied to enhance systems for speaker recognition.

Scribble Tracker: A Matting-Based Approach for Robust Tracking

Model updating is a critical problem in tracking. Inaccurate extraction of the foreground and background information in model adaptation would cause the model to drift and degrade the tracking performance. The most direct yet difficult solution to the drift problem is to obtain accurate boundaries of the target. We approach such a solution by proposing a novel model adaptation framework based on the combination of matting and tracking. In our framework, coarse tracking results automatically provide sufficient and accurate scribbles for matting, which makes matting applicable in a tracking system. Meanwhile, accurate boundaries of the target can be obtained from matting results even when the target has large deformation. An effective model combining short-term features and long-term appearances is further constructed and successfully updated based on such accurate boundaries. The model can successfully handle occlusion by explicit inference. Extensive experiments show that our adaptation scheme largely avoids model drift and significantly outperforms other discriminative tracking models.

Combining speech attribute detection and penalized logistic regression for phoneme recognition

Over the past few years, there has been a resurgence of interest in designing high-accuracy automatic speech recognition (ASR) systems due to the key rule they can play in many real-world applications, such as voice print for biometric identification, language identification, and call-scanning. Improving current state-of-the-art technology is therefore vital for the success of those aforementioned applications, yet this is not simple with the standard technology based on hidden Markov models (HMMs) trained on short-term spectral features. This paper offers an innovative prospective on how two novel prominent approaches to ASR, namely speech attribute detection and discriminative training, can be combined into a unified framework with beneficial effects on the overall speech recognition performance. This goal is achieved by embedding phonetic feature detection into a penalized logistic regression machine (PLRM). The proposed approach is evaluated on both isolated and continuous phoneme recognition tasks. Experimental evidence indicate that the proposed framework is able to achieve state-of-the-art performance in the isolated speech recognition task and to outperform current technology in the continuous speech recognition task.

Mutual Fund Ownership, Firm Specific Information, and Firm Performance: Evidence from China

This paper shows empirically that the positive association between mutual fund ownership and firm value in China is mainly driven by the informed trading of mutual funds. Utilizing the unique short term feature of mutual fund holdings for the period from 2001 to 2010, we provide an informational link between a decomposed component of market-to-book ratio (firm specific valuation component) and mutual fund holdings. Specifically, we find that firms with a higher level of mutual fund ownership are associated with a higher specific value. Moreover, the positive association between the specific value of a firm and mutual fund ownership is more pronounced in firms with a higher level of specific information (or higher idiosyncratic volatility). We argue that in an emerging market such as China, mutual funds help to improve market efficiency by incorporating private information into stock prices through their informed trading although they are really a lack of incentive to monitor management.

Short-term Feature Space and Music Genre Classification

In music genre classification, most approaches rely on statistical characteristics of low-level features computed on short audio frames. In these methods, it is implicitly considered that frames carry equally relevant information loads and that either individual frames, or distributions thereof, somehow capture the specificities of each genre. In this paper we study the representation space defined by short-term audio features with respect to class boundaries, and compare different processing techniques to partition this space. These partitions are evaluated in terms of accuracy on two genre classification tasks, with several types of classifiers. Experiments show that a randomized and unsupervised partition of the space, used in conjunction with a Markov Model classifier lead to accuracies comparable to the state of the art. We also show that unsupervised partitions of the space tend to create less hubs.

A double-branching model applied to long-term forecasting of Italian seismicity (ML≥5.0) within the CSEP project

The purpose of this study was to apply a double-branching model to forecasting of moderate-to-large Italian seismicity within the Collaboratory Study for Earthquake Predictability project. This project is designed for statistical evaluations and comparisons of various forecasting models, on both the global and regional scales. This proposed double-branching model is time-dependent, as it assumes that each earthquake can generate, or is correlated with, other earthquakes through physical mechanisms that act on different spatio-temporal scales. Specifically, it consists of an application of two branching processes, in which any earthquake can trigger a family of later events on different space-time scales. In our recent study [Lombardi and Marzocchi 2009], we applied this model to a declustered historical database that included the strong Italian seismicity from over the last few centuries. This catalog only allowed us to describe the long-term time evolution of moderate-to-strong seismicity. Here, we have applied this double-branching model to a new database that has allowed us to describe both short-term clustering and long-term features at the same time. As the model can produce forecasting calculations of future seismicity, we provide some probability maps of occurrence of predicted events over different temporal windows.