A Review on Scream Classification for Situation Understanding

Abstract

Abstract-In our living environment, a non-speech audio signal provides a significant evidence for situation awareness. It also compliments the information obtained from a video signal. In non-speech audio signals, screaming is one of the events in which the people like security guard, care taker and family members are particularly interested in terms of care and surveillance because screams are atomically considered as a sign of danger. Contrary to this concept, this review is particularly targeting automated acoustic systems using non-speech class of scream believing that the screams can further be classified into various classes like happiness, sadness, fear, danger, etc. Inspired by the prevalent scream audio detection and classification field, a taxonomy has been projected to highlight the target applications, significant sound features, classification techniques, and their impact on classification problems in last few decades. This review will assist the researchers for retrieving the most appropriate scream detection and classification technique and acoustic parameters for scream classification that can assist in understanding the vocalization condition of the speaker.

A Review on Scream Detection and Classification

“…The primary focus is on machine learning, classification methods, and crucial sound parameters for scream-centric audio systems. While the recommended approach suggests using the unsupervised learning technique, particularly GMM, incorporating spectral sound features like MFCC in surveillance, it is crucial to recognize potential risks linked to high scream detection rates in surveillance systems [26]. These conclusions are derived from diverse datasets, using various combinations of sound parameters and classification techniques, and outcomes may vary based on dataset specifics and background noise levels.…”

An Initial Machine Learning-Based Victim’s Scream Detection Analysis for Burning Sites

“…We examined support vector machines (SVM) and long short-term memory (LSTM) performance for our scream classification model. SVM was selected based on the previous research discussed in Section 2.3 and review paper in [49], which suggests SVM has outperformed neural networks in scream detection. Additionally, SVM is a much simpler model which makes it suitable for implementation on AESV [34].…”

“…Mel-frequency cepstral coefficients (MFCCs): MFCCs have been widely used in previous research on scream detection [49]. These features have received immense popularity for their relevance to human auditory perception.…”

Influence of Perceived Benefits on Consumers' Online Purchase Behaviour

“…Chakraborty (2016)statedthatthereasonablecostoftheproductatthedoorstepisthemostimportantfactor affectingtheconsumerpurchasedecisionatthetimeofonlineshopping.Theothermostimportant factorssuchasproductsareavailable24/7,savestime,andeaseincancellationorreturnarealso influencingtheconsumers'intentionstoshoponline (RaoandPatro,2017). Nazir,Tayyab,Sajid, Rashid,&Javed(2012)identifiedpricetobethemostfascinatingandaffectingfactorforthemajority ofstudentsandthegeneralpublicfollowingtrust,convenienceandrecommendationsasotherimportant factors. MeeandHuei(2015)studyrevealedthatInternetshoppersrespondpositivelytowardsthe motivationalandattitudeaspectsofonlineshoppingcomparedtothenon-internetshoppers.The internetshoppersseekmoreconveniencethannon-internetshoppers,followedbyinnovativeness, impulsiveness, variety seeking, attitude towards online shopping, and attitude towards online advertising.Theotherfactorswhichhadamoderateinfluenceonconsumers'attitudearesecurity, saleservice,anddiscounteddeals (Patro,2017).…”