A DNN based Normalized Time-frequency Weighted Criterion for Robust Wideband DoA Estimation

TL;DR

This paper introduces a robust DNN-based wideband DoA estimation method using a normalized T-F weighted criterion that enhances accuracy in noisy, reverberant environments without eigendecomposition.

Contribution

The paper proposes a novel normalized T-F weighted criterion for DNN-based DoA estimation that improves robustness against interference and outperforms existing methods.

Findings

Outperforms popular DNN-based DoA methods in noisy environments

Duplicating Hadamard product of speech masks is highly effective

No eigendecomposition required for the proposed method

Abstract

Deep neural networks (DNNs) have greatly benefited direction of arrival (DoA) estimation methods for speech source localization in noisy environments. However, their localization accuracy is still far from satisfactory due to the vulnerability to nonspeech interference. To improve the robustness against interference, we propose a DNN based normalized time-frequency (T-F) weighted criterion which minimizes the distance between the candidate steering vectors and the filtered snapshots in the T-F domain. Our method requires no eigendecomposition and uses a simple normalization to prevent the optimization objective from being misled by noisy filtered snapshots. We also study different designs of T-F weights guided by a DNN. We find that duplicating the Hadamard product of speech ratio masks is highly effective and better than other techniques such as direct masking and taking the mean in the proposed approach. However, the best-performing design of T-F weights is criterion-dependent in general. Experiments show that the proposed method outperforms popular DNN based DoA estimation methods including widely used subspace methods in noisy and reverberant environments.