Acoustic Source Localization using Random Forest Regressor
Minu A. Pillai, Alwyn Ghosh, Jestin Joy, Suraj Kamal, C. Satheesh Chandran, Arun A. Balakrishnan, M. H. Supriya · 2019
In this paper, a machine learning based acoustic source localization in an indoor environment is presented. Acoustic source localization is considered as a supervised learning problem and is solved by random forest regressor. Experiments have been conducted to collect narrow band audio signals from an acoustic source placed at different angles using a linear array of 8 microphones. The model is trained using the signals captured by the microphone array. Finally, the performance of the model has been evaluated on an independent test set and results show that the random forest regressor model can be effectively used for indoor acoustic source localization.