In this paper we explore the use of features derived from multiresolution analysis of speech and the Teager Energy Operator for classiication of drivers' speech under stressed conditions. The potential stress categories are determined by driving speed and the frequency with which the driver has to solve a mental task while driving. We rst use an unsupervised approach to gain some understanding ...

In this paper, novel Variable length Teager Energy Operator (VTEO) based Mel cepstral features, viz., VTMFCC are proposed for automatic classification of normal and pathological voices. Experiments have been carried out using this proposed feature set, MFCC and their score-level fusion. Classification was performed using a 2 order polynomial classifier on a subset of the MEEI database. The equa...

This paper mainly addresses the problem of determining voice activity in presence of noise, especially in a dynamically varying background noise. The proposed voice activity detection algorithm is based on structure of three-layer wavelet decomposition. Appling auto-correlation function into each subband exploits the fact that intensity of periodicity is more significant in sub-band domain than...

This paper exploits the novelty detection technique towards identifying hazardous situations. The proposed system elaborates on the audio part of the PROMETHEUS database which includes heterogeneous recordings and was captured under real-world conditions. Three types of environments were used: smart-home, indoors public space and outdoors public space. The multidomain set of descriptors was for...

As an important part of our daily life, speech has a great impact on the way people communicate. The Mel filter bank used in extraction process MFCC better ability to low-frequency component signal, but it weakens emotional information contained high-frequency signal. We inverted enhance feature processing signal obtain IMFCC coefficients and fuse features order I_MFCC. Finally, more accurately...

-This paper presents a novel algorithm for automatic QRS complex detection and premature ventricular contraction (PVC) beat recognition based on a generalised Teager energy operator (GTEO). The algorithm is divided into two stages: QRS detection and PVC beat recognition. An optimal GTEO order is determined for each stage. A second order GTEO is used for QRS detection, and a seventh order GTEO i...

PURPOSE The primary aim of this study is to investigate the potential benefit of the Teager-Kaiser Energy Operator (TKEO) as data pre-processor, in an autonomous burst detection method to classify electromyographic signals of the (fore)arm and hand. For this purpose, optimal settings of the burst detector, leading to minimal detection errors, need to be known. Additionally, the burst detector i...

In this paper are described the most commonly encountered algorithm for pitch detection. We restrict ourselves exclusively to monophonic sound source. Both frequency and time domain algorithm are explored. The techniques presented here are zero-crossing, autocorrelation function, average magnitude difference function, weighted autocorrelation function, harmonic product spectrum, cepstrum and th...

This study examines the difficult task of Speech Activity Detection (SAD) in two hostile environments: AM push-to-talk air traffic control and international telephone conversations with very low SNRs. Due to the poor performance of traditional energy-based SAD, two novel approaches to SAD were developed that specifically target spectral characteristics that typify speech, rather than trying to ...