DeepAI AI Chat
Log In Sign Up

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

by   Luca Mazzon, et al.

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


page 1

page 2

page 3

page 4


Dynamic Data Augmentation with Gating Networks

Data augmentation is a technique to improve the generalization ability o...

Semantic Equivariant Mixup

Mixup is a well-established data augmentation technique, which can exten...

Signed Input Regularization

Over-parameterized deep models usually over-fit to a given training dist...

InAugment: Improving Classifiers via Internal Augmentation

Image augmentation techniques apply transformation functions such as rot...

Multiple source direction of arrival estimation using subspace pseudointensity vectors

The recently proposed subspace pseudointensity method for direction of a...

Augmented Transformer Achieves 97 and Classical Retro-Synthesis

We investigated the effect of different augmentation scenarios on predic...