Scream detection for home applications

Abstract

Audio signal is an important clue for the situation awareness. It provides complementary information for video signal. For home care, elder care, and security application, screaming is one of the events people (family member, care giver, and security guard) are especially interested in. We present here an approach to scream detection, using both analytic and statistical features for the classification. In audio features, sound energy is a useful feature to detect scream like audio. We adopt the log energy to detect the energy continuity of the audio to represent the screaming which is often lasting longer than many other sounds. Further, a robust high pitch detection based on the autocorrelation is presented to extract the highest pitch for each frame, followed by a pitch analysis for a time window containing multiple frames. Finally, to validate the scream like sound, a SVM based classifier is applied with the feature vector generated from the MFCCs across a window of frames. Experiments of screaming detection is discussed with promising results shown. The algorithm is ported and run in a Linux based set top box connected by a microphone array to capture the audio for live scream detection.

Human Scream Detection and Analysis to Control Crime Rate using Machine Learning

“…In [6] they employed analytical features followed by SVM classification for event identification, while [7] utilized MFCC, MPEG-7 features, and Hidden Markov Models (HMMs) for gunshot and scream classification. A parallel GMM classifier network achieved a reported 90% accuracy with an 8% false alarm rate in [8].…”

Deep Learning-Based Portable Device for Audio Distress Signal Recognition in Urban Areas

“…These results are comparable to the ones obtained by other works that implemented real-time applications of audio processing. Examples include audio processing times for real-time predictions of around 1000 ms in [6], and between 104 to 1360 ms in [22].…”

“…For example, the database presented in [5] includes audios with utterances of emotional speech. Moreover, the databases presented in [6,7] include audios that are labeled with different types of emotions and recorded in low noise environments as houses or closed locations. The work in [8] presented a large database that includes screaming sounds that were artificially overlapped with white additive Gaussian noise.…”

Deep Convolutional Neural Networks for the Classification and Detection of Human Vocal Exclamations of Panic in Subway Systems

“…Automated systems can be used to detect exclamations of panic in an emergency and distinguish them from sounds from people quarreling or talking loudly; these systems are useful in subway systems because they can help station staff detect and react to emergencies quickly [1]. Thus, in the present study, we developed a convolutional neural network (CNN) that classifies and detects panicked vocalizations on the mass rapid transit (MRT) system in Taipei.…”