Online Direction of Arrival Estimation Based on Deep Learning

Abstract

Direction of arrival (DOA) estimation is an important topic in microphone array processing. Conventional methods work well in relatively clean conditions but suffer from noise and reverberation distortions. Recently, deep learning-based methods show the robustness to noise and reverberation. However, the performance is degraded rapidly or even model cannot work when microphone array structure changes. So it has to retrain the model with new data, which is a huge work. In this paper, we propose a supervised learning algorithm for DOA estimation combining convolutional neural network (CNN) and long short term memory (LSTM). Experimental results show that the proposed method can improve the accuracy significantly. In addition, due to an input feature design, the proposed method can adapt to a new microphone array conveniently only use a very small amount of data.