First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation
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%.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDirection of Arrival EstimationSimilar Papers 제목 키워드 기반
ViSAGe: Video-to-Spatial Audio Generation
Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem o…
Audio GenerationThe role of direct sound spherical harmonics representation in externalization using binaural reproduction
The importance of the information in the direct sound to human perception of spatial sound sources is an ongoing research topic. The classification between direct sound and diffuse or reverberant sound forms the basis of…
Direction of Arrival Estimation of Noisy Speech Using Convolutional Recurrent Neural Networks with Higher-Order Ambisonics Signals
Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasi…
Direction of Arrival EstimationiMagLS: Interaural Level Difference with Magnitude Least-Squares Loss for Optimized First-Order Head-Related Transfer Function
Binaural reproduction for headphone-based listening is an active research area due to its widespread use in evolving technologies such as augmented and virtual reality (AR and VR). On the one hand, these applications dem…
Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection
Data augmentation methods have shown great importance in diverse supervised learning problems where labeled data is scarce or costly to obtain. For sound event localization and detection (SELD) tasks several augmentation…
Data AugmentationSound Event Localization and Detection