Search results for "Mel-frequency cepstrum"
showing 3 items of 13 documents
Emergency Detection with Environment Sound Using Deep Convolutional Neural Networks
2020
In this paper, we propose a generic emergency detection system using only the sound produced in the environment. For this task, we employ multiple audio feature extraction techniques like the mel-frequency cepstral coefficients, gammatone frequency cepstral coefficients, constant Q-transform and chromagram. After feature extraction, a deep convolutional neural network (CNN) is used to classify an audio signal as a potential emergency situation or not. The entire model is based on our previous work that sets the new state of the art in the environment sound classification (ESC) task (Our paper is under review in the IEEE/ACM Transactions on Audio, Speech and Language Processing and also avai…
Event signal characterization for disturbance interpretation in power grid
2018
This paper presents the signal processing approach to detect and characterize the physical events that occur in power system using PMUs signals. A small window is applied so that the extracted spectral features belong to a stationary signal. This is based on applying empirical mode decomposition, followed by square root of spectral kurtosis (SRSK) for computation of statistical indices to indicate the event occurrence. Subsequently, features from these events are extracted using mel frequency cepstral coefficients on SRSK. © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/re…
EEG-based biometrics: effects of template ageing
2020
This chapter discusses the effects of template ageing in EEG-based biometrics. The chapter also serves as an introduction to general biometrics and its main tasks: Identification and verification. To do so, we investigate different characterisations of EEG signals and examine the difference of performance in subject identification between single session and cross-session identification experiments. In order to do this, EEG signals are characterised with common state-of-the-art features, i.e. Mel Frequency Cepstral Coefficients (MFCC), Autoregression Coefficients, and Power Spectral Density-derived features. The samples were later classified using various classifiers, including Support Vecto…