Deep neural networks for automatic detection of screams and shouted speech in subway trains

• Published in: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6460 - 6464
• Main Authors: Laffitte, Pierre, Sodoyer, David, Tatkeu, Charles, Girin, Laurent
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.03.2016
• Subjects: Acoustics; audio event detection; Automation; Classification; Deep Belief Networks; Electronics; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Neural networks; Public transportation; scream detection; Speech; Subway cars; Support vector machines; transport environment
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP.2016.7472921

Deep Neural Networks (DNNs) have recently become a popular technique for regression and classification problems. Their capacity to learn high-order correlations between input and output data proves to be very powerful for automatic speech recognition. In this paper we investigate the use of DNNs for automatic scream and shouted speech detection, within the framework of surveillance systems in public transportation. We recorded a database of sounds occurring in subway trains in real conditions of exploitation and used DNNs to classify the sounds into screams, shouts and other categories. We report encouraging results, given the difficulty of the task, especially when a high level of surrounding noise is present.