# DBNET: DOA-driven beamforming network for end-to-end farfield sound source separation

arXiv: https://arxiv.org/abs/2010.11566 · HTML: https://mlsanity.com/paper/2010.11566/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment](https://mlsanity.com/paper/2202.10372/) (2022)
- [L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing](https://mlsanity.com/paper/2104.05499/) (2021)
- [Learning Filterbanks for End-to-End Acoustic Beamforming](https://mlsanity.com/paper/2111.04614/) (2021)

## Abstract (arXiv)

Many deep learning techniques are available to perform source separation and reduce background noise. However, designing an end-to-end multi-channel source separation method using deep learning and conventional acoustic signal processing techniques still remains challenging. In this paper we propose a direction-of-arrival-driven beamforming network (DBnet) consisting of direction-of-arrival (DOA) estimation and beamforming layers for end-to-end source separation. We propose to train DBnet using loss functions that are solely based on the distances between the separated speech signals and the target speech signals, without a need for the ground-truth DOAs of speakers. To improve the source separation performance, we also propose end-to-end extensions of DBnet which incorporate post masking networks. We evaluate the proposed DBnet and its extensions on a very challenging dataset, targeting realistic far-field sound source separation in reverberant and noisy environments. The experimental results show that the proposed extended DBnet using a convolutional-recurrent post masking network outperforms state-of-the-art source separation methods.