Detection of Emergency Signal in Hearing Aids using Neural Networks

Abstract: ABSTRACT The detection of an emergency signal can be estimated by the cancellation of surrounding noise and achieving the desired signal in order to alert the automobilist. The aim of the thesis is to detect the emergency signal arriving nearer to the automobilist carrying hearing aids. Recent studies show that this can be achieved by designing various kinds of fixed and adaptive beam formers. A beam former does spatial filtering in the sense that it separates two signals with overlapping frequency content originating from distinctive directions. In this contribution, robust beam former namely Wiener beam former is designed and analyzed collaboratively in a group under the consideration of hearing aid constraints such as the microphone distance. A fractionally delay (FD) are designed to get a maximally flat group delay. The studies had been carried out by comparing noise cancellation algorithms like LMS, NLMS, LLMS and RLS algorithms. By comparing Omni-directional and multi-directional microphones the SNR can be studied. In this thesis work, first proposing appropriate microphone array setup with improved beam forming techniques by using required adaptive algorithm (NLMS) in order to get better quality using the Microphone arrays. Microphone arrays have been widely used to improve the performance of speech recognition systems as well as to benefit for people who need hearing aids. With the help of microphone arrays, it can choose to focus on signals from a specific direction. To getting better signal quality in microphone array using adaptive algorithms, these are help in the noise suppression in accordance with the different beam forming techniques. The proposed system is implemented successfully and validated using MATLAB simulation tool. The emergency signal is different in different countries, so we identify any type of emergency signal by training through neural networks.