Abstract
As for situation responsiveness, audio and video signals are very important. Audio is significant because it can enlighten us concerning situations, character, time, and place. The study describes a distress audio (scream or shout) event classification system which precisely classifies an audio event as ambient noise, screams, and shouts. Scream is a high-pitch vocalized sound in the absence of phonological structure. This study, researched the classification system using a three-phase SVM-based classifier model for segregating human distress sound from noise and then scream from a shout. The training of SVM-based classifier is done with audio MFCC as feature vectors, appropriately chosen from a set of 400 audio sets, which are selected according to a two-phase process. A classifier is trained and tested with each feature subset. SVM-based classifier analyses and predicts the sound which works with linear kernel and radial basis function (rbf) kernel. The obtained classification performance then again passes through the Multilayer Perceptron Model. When the model gets any sound then it tries to identify patterns in it using perceptron weights and biases if it can’t get success it slightly changes its weights for getting the correct result if it successfully detects a scream in sound then it calls the emergency function. Our results demonstrate that the system can generate a 90% accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
M.K. Nandwana, A. Ziaei, J.H. Hansen, Robust unsupervised detection of human screams in noisy acoustic environments, in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2015), pp. 161–165
G. Valenzise, L. Gerosa, M. Tagliasacchi, F. Antonacci, A. Sarti, Scream and gunshot detection and localization for audio-surveillance systems, in 2007 IEEE Conference on Advanced Video and Signal Based Surveillance (IEEE, 2007), pp. 21–26
S. Ntalampiras, I. Potamitis, N. Fakotakis, On acoustic surveillance of hazardous situations, in IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 165–168 (2009)
M.A. Sehili, B. Lecouteux, M. Vacher, F. Portet, D. Istrate, B. Dorizzi, J. Boudy, Sound environment analysis in smart home, in International Joint Conference on Ambient Intelligence (Springer, Berlin, Heidelberg, 2012), pp. 208–223
H.D. Tran, H. Li, Sound event recognition with probabilistic distance SVMs. IEEE Trans. Audio Speech Lang. Process. 19(6), 1556–1568 (2010)
W. Huang, T.K. Chiew, H. Li, T.S. Kok, J. Biswas, Scream detection for home applications, in 2010 5th IEEE Conference on Industrial Electronics and Applications (IEEE, 2010), pp. 2115–2120
S. Ntalampiras, I. Potamitis, N. Fakotakis, On acoustic surveillance of hazardous situations, in 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 165–168
L. Gerosa, G. Valenzise, M. Tagliasacchi, F. Antonacci, A. Sarti, Scream and gunshot detection in noisy environments, in 2007 15th European Signal Processing Conference (IEEE, 2007), pp. 1216–1220
J. Pohjalainen, P. Alku, T. Kinnunen, Shout detection in noise, in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2011), pp. 4968–4971
.K. Mittal, B. Yegnanarayana, Production features for detection of shouted speech, in 2013 IEEE 10th Consumer Communications and Networking Conference (CCNC) (IEEE, 2013), pp. 106–111
A. Sharma, S. Kaul, Two-stage supervised learning-based method to detect screams and cries in urban environments. IEEE/ACM Trans. Audio Speech Lang. Process. 24(2), 290–299 (2015)
S. Chung, Y. Chung, Scream sound detection based on SVM and GMM, in RTET-17, 2017
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shankhdhar, A., Rachit, Kumar, V., Mathur, Y. (2021). Human Scream Detection Through Three-Stage Supervised Learning and Deep Learning. In: Suma, V., Chen, J.IZ., Baig, Z., Wang, H. (eds) Inventive Systems and Control. Lecture Notes in Networks and Systems, vol 204. Springer, Singapore. https://doi.org/10.1007/978-981-16-1395-1_28
Download citation
DOI: https://doi.org/10.1007/978-981-16-1395-1_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1394-4
Online ISBN: 978-981-16-1395-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)