First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation

Abstract

In this paper, we propose a novel data augmentation method for training neural networks for Direction of Arrival (DOA) estimation. This method focuses on expanding the representation of the DOA subspace of a dataset. Given some input data, it applies a transformation to it in order to change its DOA information and simulate new potentially unseen one. Such transformation, in general, is a combination of a rotation and a reflection. It is possible to apply such transformation due to a well-known property of First Order Ambisonics (FOA). The same transformation is applied also to the labels, in order to maintain consistency between input data and target labels. Three methods with different level of generality are proposed for applying this augmentation principle. Experiments are conducted on two different DOA networks. Results of both experiments demonstrate the effectiveness of the novel augmentation strategy by improving the DOA error by around 40%.

arXiv comment5 pages, to appear in DCASE 2019

References in corpus (5)

• mixup: Beyond Empirical Risk Minimization
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
• Deep Neural Networks for Multiple Speaker Detection and Localization
• Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy

Cited by in corpus (3)

• A Survey of Sound Source Localization with Deep Learning Methods
• An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection
• L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing