Alcohol use disorder detection using EEG Signal features and flexible analytical wavelet transform

In this paper, we introduce subband likelihood-maximizing beamforming (S-LIMABEAM), a new microphone-array processing algorithm specifically designed for speech recognition applications. The proposed algorithm is an extension of the previously developed LIMABEAM array processing algorithm. Unlike most array processing algorithms which operate according to some waveform-level objective function, the goal of LIMABEAM is to find the set of array parameters that maximizes the likelihood of the correct recognition hypothesis. Optimizing the array parameters in this manner results in significant improvements in recognition accuracy over conventional array processing methods when speech is corrupted by additive noise and moderate levels of reverberation. Despite the success of the LIMABEAM algorithm in such environments, little improvement was achieved in highly reverberant environments. In such situations where the noise is highly correlated to the speech signal and the number of filter parameters to estimate is large, subband processing has been used to improve the performance of LMS-type adaptive filtering algorithms. We use subband processing principles to design a novel array processing architecture in which select groups of subbands are processed jointly to maximize the likelihood of the resulting speech recognition features, as measured by the recognizer itself. By creating a subband filtering architecture that explicitly accounts for the manner in which recognition features are computed, we can effectively apply the LIMABEAM framework to highly reverberant environments. By doing so, we are able to achieve improvements in word error rate of over 20% compared to conventional methods in highly reverberant environments

/pdf/subband-likelihood-maximizing-beamforming-for-speech-4r9sjnlz8x.pdf

Subband Likelihood-Maximizing Beamforming for Speech Recognition in Reverberant Environments

Estimation of wavelet and short-time Fourier transform sonograms of normal and diabetic subjects' electrogastrogram.

Spectral analysis of ground penetrating radar signals in concrete, metallic and plastic targets

Diagnosis of engine component faults is a challenging task for every researcher due to the complexity involved in the engine operations. The developed faults on the engine components subsequently reduce their performance and cause higher maintenance costs. Hence, an effective condition monitoring technique should be implemented to diagnose engine component faults. Therefore, in this work, potential fault diagnosis techniques are presented to detect and diagnose the scuffing faults developed on the diesel engine components. Condition monitoring techniques such as vibration and acoustic emission analyses were employed to acquire the fault-related signals. These signals were analyzed in the time-domain, frequency-domain, and time–frequency domain using signal processing methods viz. fast Fourier transform (FFT) and short-time Fourier transform (STFT). The statistical feature parameters were also extracted from the acquired signals to diagnose the severity of the faults. Further, the artificial neural network (ANN) models were developed to predict and classify the scuffing faults developed on the engine components. The results showed that the FFT and STFT techniques provide better fault diagnostic information. The developed neural network models have effectively classified the scuffing faults on engine components with an accuracy of 100%.

F. J. Owens

Papers

A short-time Fourier transform