CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation

Key points

• Classification- based DOA methods discretize the continuous angular space into a grid, so that with a peak-based read-out, the accuracy and resolution are limited by the grid step and by the width of the label peak.1
• To address this issue, we propose a sigmoid label that encodes the sources' DOAs as the sum of angle-shifted monotonic sigmoid functions.1
• Combined with a moderately refined grid step of 0.25 degrees, the CNN-Transformer with the proposed sigmoid label attains sub-degree accuracy and a 1-degree resolution, breaking the limit of the grid quantization error.1
• Under the unified CNN-Transformer backbone, we compare the proposed Sigmoid label with the Gaussian label, the 0-1 hard label, and the binary cross-entropy (BCE) baseline.1

Sources (1)

• [1]CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 11:34 AM

  This paper addresses the grid quantization error of deep-learning (DL)-based direction-of-arrival (DOA) estimation.

  Classification- based DOA methods discretize the continuous angular space into a grid, so that with a peak-based read-out, the accuracy and resolution are limited by the grid step and by the width of the label peak.

Extractive summary: sentences quoted from the sources.