Search

In both pattern recognition and artificial intelligence, audio identification has very broad theoretical and practical values. The noise from the surrounding area such as transportation, weather, and people's action affected the interruption in signal processing. Current traffic light system is lack of information when a vehicle is in emergencies such as ambulance, firefighter, and police. This paper is designed to develop an embedded machine learning application, including data acquisition, extraction of features, exploration of different algorithms, tuning for a good performance model and deploying the model in a simulation application. Specifically, a classifier of ambulance siren sound into 'Ambulance Arrive' and 'No Ambulance Arrive' has been developed, which could be used in the traffic light system to monitor the arrival of an ambulance which in an emergency. This paper suggests an approach based on Mel-frequency cepstral coefficients-Support Vector Machine (MFCC-SVM) on MATLAB R2017b tools that take advantage of the effect of feature representation and learner optimization tasks to effectively distinguish audio events from audio signals. [ABSTRACT FROM AUTHOR]

Deep learning is an emerging technology that is one of the most promising areas of artificial intelligence. Great strides have been made in recent years which resulted in increased efficiency with regards to many applications, including speech. Despite this, an environmentally Robust Speech Recognition system is still far from being achieved. In this article, an investigation of previous work has been conducted. The use of deep learning in speech recognition was analyzed and a proper deep learning architecture was identified. A method using convolutional neural network (CNN) is used with the aim of enhancing the performance of speech recognition systems (SRS). This study found that this CNN-based approach achieves a 94.32% validated accuracy [ABSTRACT FROM AUTHOR]