DeepAI AI Chat
Log In Sign Up

Regression and Classification for Direction-of-Arrival Estimation with Convolutional Recurrent Neural Networks

by   Zhenyu Tang, et al.
University of Maryland

We present a novel learning-based approach to estimate the direction-of-arrival (DOA) of a sound source using a convolutional recurrent neural network (CRNN) trained via regression on synthetic data and Cartesian labels. We also describe an improved method to generate synthetic data to train the neural network using state-of-the-art sound propagation algorithms that model specular as well as diffuse reflections of sound. We compare our model against three other CRNNs trained using different formulations of the same problem: classification on categorical labels, and regression on spherical coordinate labels. In practice, our model achieves up to 43 angular error over prior methods. The use of diffuse reflection results in 34 and 41 respectively, over prior methods based on image-source methods. Our method results in an additional 3 classification based networks, and we use 36


Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network

This paper proposes a deep neural network for estimating the directions ...

Temporal Overdrive Recurrent Neural Network

In this work we present a novel recurrent neural network architecture de...

CRNNTL: convolutional recurrent neural network and transfer learning for QSAR modelling

In this study, we propose the convolutional recurrent neural network and...

Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs

In this paper, we present a new model for Direction of Arrival (DOA) est...

Joint Direction and Proximity Classification of Overlapping Sound Events from Binaural Audio

Sound source proximity and distance estimation are of great interest in ...