Noise-robust scream detection using band-limited spectral entropy

A Review on Scream Classification for Situation Understanding

“…Zaheer et al [14] achieved 100% scream detection accuracy with GMM technique. Another classification technique used by N. Hayasaka et al [4] achieved an accuracy rate of 99% again with GMM. The overall average accuracies of the four un-supervised scream classifiers are calculated and plotted in Fig.…”

“…7 shows the percentage accuracies of each technique along with the authors and references independently. N. Hayasaka et al [4] is leading while using SVMs with accuracy rate of 94.6%. …”

“…In more complicated and complex signals such as speech or music where the signal changes its properties over time, it is evidently more meaningful to refer to the altering frequency content over a smaller time interval than an infinite time interval. Spectral Flux E. R. Siebert et al [29], L. Gerosa et al [2],, M. Z. Zaheer et al [14], R. A. Breguet et al [31] Spectral Tilt L. Gerosa et al [2], R. A. Breguet et al [31], C. Zhang et al [25] Spectral Entropy M. Mark et al [21], A. Pillai et al [8] , N. Hayasaka et al [4], W. Liao et al [23] Signal Bandwidth M. Mark et al [21], W. Liao et al [23] Sub-Band Energy Ratio J. H. L. Hansen et al [1], C. Chan et al [22], M. Z. Zaheer et al [14], C. Zhang et al [25] Linear Prediction P. C. Schön et al [27], N. E. O. Connor et al [30] Prosodic Pitch/Fundamental Frequency M. Mark et al [21], L. H. Arnal et al [7] , C. Chan et al [22], L. Gerosa et al [2], J. H. L. Hansen et al [13], M. Z. Zaheer et al [14], K. Kato [19], B. Uzkent et al [20], W. Liao et al [23] Loudness/Intensity L. Gerosa et al [2], K. Kato [19], C. Zhang et al [25] Rhythm/Duration C. Chan et al [22], K. Kato [19], C. Zhang et al [25] Log Energy N. Hayasaka et al [4], W. Huang et al [3] 0.0% 70 | P a g e www.ijacsa.thesai.org …”

“…Those classification problems that have hindered the further development and exploration in screaming environments, are discussed. 4 The selected data has been divided into different categories to carve out possible alternatives in several directions. Table I presents literature works related to the scenarios using scream detection or classification as major.…”

“…Different techniques and methodologies have been established to differentiate speech and non-speech sounds. These include Support Vector Machines [3], band-limited spectral entropy [4], Deep Neural Networks (DNN) [5], Hidden Markov Model (HMM), sound event partitioning [6] and modulation power spectrum [7].…”