Broadband DOA estimation using Convolutional neural networks trained with noise signals
This work addresses DOA estimation for acoustic signal processing, offering a more convenient training approach but is incremental in method.
The paper tackled broadband direction-of-arrival (DOA) estimation by proposing a convolutional neural network (CNN) method trained with synthesized noise signals, demonstrating generalization to speech sources and robustness to noise and microphone perturbations in experiments.
A convolution neural network (CNN) based classification method for broadband DOA estimation is proposed, where the phase component of the short-time Fourier transform coefficients of the received microphone signals are directly fed into the CNN and the features required for DOA estimation are learnt during training. Since only the phase component of the input is used, the CNN can be trained with synthesized noise signals, thereby making the preparation of the training data set easier compared to using speech signals. Through experimental evaluation, the ability of the proposed noise trained CNN framework to generalize to speech sources is demonstrated. In addition, the robustness of the system to noise, small perturbations in microphone positions, as well as its ability to adapt to different acoustic conditions is investigated using experiments with simulated and real data.