Sound Source Localization Inside a Structure Under Semi-Supervised Conditions

Abstract

We propose a method for applying a sound source localization (SSL) model trained on simulated data in a real-world environment, with a domain transfer (DT) model for the SSL inside a product structure. The DT model transfers real data into pseudo-simulation data. The SSL model trained on the simulation data is then adapted to the real data using the DT model. As such, our method consists of an SSL model and a DT model. The SSL model predicts the position of a sound source inside the structure, whereas the DT model transforms the data. Because our simulation is not perfect, real data are extrapolated for use with the SSL model. However, the data transformed by the DT model are interpolated within the feature space. The outcome is that the performance of the SSL model in the real world is improved. In our study, the frequency spectra of accelerometers observed on the outer surface of the structure are the model input. The goal is to predict the position of the sound source. The SSL model is built using deep and convolutional neural networks, and the DT model is built using either an autoencoder, a deep convolutional autoencoder, or pix2pix. The two-dimensional distributions of the t-distributed Stochastic Neighbor Embedding indicate that using pix2pix as the DT model shows the best performance. Furthermore, our method's performance for SSL is improved by 57% for the classification problem and by 27% for the regression problem when compared to the case where no transformation is applied.