1,720,967 research outputs found
Tecniche non Monte Carlo per la simulazione statistica di circuiti integrati mixed-signal
No full textAnalysis of the EMG Signal During Cyclic Movements Using Multicomponent AM-FM Decomposition
No full textSport, fitness, as well as rehabilitation activities, often require the accomplishment of repetitive movements. The correctness of the exercises is often related to the capability of maintaining the required cadence and muscular force. Failure to maintain the required force, also known as muscle fatigue, is accompanied by a shift in the spectral content of the surface electromyography (EMG) signal towards lower frequencies. This paper presents a novel approach for simultaneously obtaining exercise repetition frequency and evaluating muscular fatigue, as functions of time, by only using the EMG signal. The mean frequency of the amplitude spectrum (MFA) of the EMG signal, considered as a function of time, is directly related to the dynamics of the movement performed and to the fatigue of the involved muscles. If the movement is cyclic, MFA will display the same pattern and its average will tend to decrease. These two effects have been simultaneously modeled by a two-component AM-FM model based on the Hilbert transform. The method was tested on signals recorded using a wireless system applied to healthy subjects performing dumbbell biceps curls, dumbbell lateral rises, and bodyweight squats. Experimental results show the excellent performance of the proposed technique
Semi-automatic acoustic model generation from large unsynchronized audio and text chunks
No full textIn this paper an effective technique to train an acoustic model from large and unsynchronized audio and text chunks is presented. Given such a speech corpus, an algorithm to automatically segment each chunk into smaller fragments and to synchronize those to the corresponding text is defined. These smaller fragments are more suitable to be used in standard model training algorithms for usage in automatic speech recognition systems. The proposed approach is particularly suitable to bootstrap language models without relying neither on specialized training material nor borrowing from models trained for other similar languages. Extensive experimentation using the CMU Sphinx 4 recognizer and the SphinxTrain model generator in a setting designed for large-vocabulary continuous speech recognition shows the effectiveness of the approach
Multi-class ECG beat classification based on a Gaussian mixture model of Karhunen-Loève transform
No full textCardiovascular diseases are one of the main causes of death around the world. Automatic classification of electrocardiogram (ECG) signals is of paramount importance in the unmanned detection of a wide range of heartbeat abnormalities. In this paper an effective multi-class beat classifier, based on a statistical identification of a minimum-complexity model, is presented. This methodology extracts from the ECG signal the multivariate relationships of its natural modes, by means of the separation property of the Karhunen-Loève transform (KLT). Then, it exploits an optimized expectation maximization (EM) algorithm to find the optimal parameters of a Gaussian mixture model, with the focus being in reducing the number of parameters. The resulting statistical model is thus based on the estimation of the multivariate probability density function (PDF) that characterizes each beat type. Based on the above statistical characterization a multi-class ECG classification was performed. The experiments, conducted on the ECG signals from the MIT-BIH arrhythmia database, demonstrated the validity and, considering the reduced model size, the excellent performance of this technique to classify the ECG signals into different disease categories
SiSMA: Simulator for Statistical Mismatch Analysis
No full textPresentato a "The University Booth" della conferenza internazionale "10th Design, Automation and Test in Europe (DATE 07)", 16-20 Aprile, 2007, Nizza, Francia
A garbage model generation technique for embedded speech recognisers
No full textIn this paper we present a simple but effective technique to help the designer of a voice-operated appliance add out-of-grammar command rejection capabilities, with a minimal effort and without overly degrading the recognition accuracy. Given the desired operational grammar of the appliance, and starting from a generic pre-trained acoustic model and comprehensive dictionary, we use a speech recogniser to identify suitable decoys to be added to the target grammar. These decoys will capture most of the spoken out-of-vocabulary words, and with appropriate changes to the desired grammar, will make the rejection of unintended commands quite easy. An evaluation of the performance of the proposed approach has been carried out on a sample appliance we developed, and tested with several users, under different acoustic conditions, in a command-spotting scenario. The reported results show that the proposed approach largely outperforms the standard phone loop-based approach
Piecewise linear second moment statistical simulation of ICs affected by non-linear statistical effects
No full textThis paper presents a methodology for statistical simulation of non-linear integrated circuits affected by device mismatch. This simulation technique is aimed at helping designers maximize yield, since it can be orders of magnitude faster than other readily available methods, e.g. Monte Carlo. Statistical analysis is performed by modeling the electrical effects of tolerances by means of stochastic current or voltage sources, which depend on both device geometry and position across the die. They alter the behavior of both linear and non-linear components according to stochastic device models, which reflect the statistical properties of circuit devices up to the second order (i.e. covariance functions). DC, AC, and transient analyses are performed by means of the stochastic modified nodal analysis, using a piecewise linear stochastic technique with respect to the stochastic sources, around a few automatically selected points. Several experimental results on significant circuits, encompassing both the analog and the digital domains, prove the effectiveness of the proposed method
Iterative Constrained MLLR Approach for Speaker Adaptation
No full textIn this paper an effective technique for speaker adaptation on the feature domain is presented. This technique starts from the well known maximum-likelihood linear regression (MLLR) auxiliary function to obtain the constrained MLLR transformation in an iterative fashion. The proposed approach is particularly suitable to be implemented on the client side of a distributed speech recognition scheme, due to the reduced number of iterations required to reach convergence. Extensive experimentation using the CMU Sphinx 4 ASR system along with a preliminarily trained speaker-independent acoustic model for the Italian language, in a setting designed for large-vocabulary continuous speech recognition, demonstrates the effectiveness of the approach even with small amounts of adaptation data
Unsupervised identification of nonstationary dynamical systems using a Gaussian mixture model based on EM clustering of SOMs
No full textIn this paper an effective unsupervised statistical identification technique for nonstationary nonlinear systems is presented. This technique extracts from the system outputs the multivariate relationships of the system natural modes, by means of the separation property of the Karhunen-Loève transform (KLT). Then, it applies a Self-Organizing Map (SOM) to the KLT output vectors in order to give an optimal representation of data. Finally, it exploits an optimized Expectation Maximization (EM) algorithm to find the optimal parameters of a Gaussian mixture model. The resulting statistical system identification is thus based on the estimation of the multivariate probability density function (PDF) of system outputs, whose convergence towards that computed by kernel estimation has also been proved by verifying the asymptotically vanishing of Kullback-Leibler divergences. A large number of simulations on ECG signals demonstrated the validity and the excellent performance of this technique along with its applicability to noninvasive diagnosis of a large class of medical pathologies originated by unknown, unpractical to measure, physiological factors
A Multi-Class ECG Beat Classifier Based on the Truncated KLT Representation
No full textAutomatic classification of electrocardiogram (ECG) signals is of paramount importance in the detection of a wide range of heartbeat abnormalities as aid to improve the diagnostic achieved by cardiologists. In this paper an effective multi-class beat classifier, based on statistical identification of a minimum-complexity model, is proposed. The classifier is trained by extracting from the ECG signal a multivariate random vector by means of a truncated Karhunen-Loève transform (KLT) representation. The resulting statistical model is thus estimated using a robust and efficient Expectation Maximization (EM) algorithm to find the optimal parameters of a Gaussian mixture model. Based on the above statistical characterization a multi-class ECG classifier was derived. The experiments, conducted on the ECG signals from the MIT-BIH arrhythmia database, demonstrated the excellent performance of this technique to classify the ECG signals into different disease categories, with a reduced model complexity
- …
