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

10/22/2020
by   Ali Aroudi, et al.
0

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.

READ FULL TEXT
research
10/08/2021

TRUNet: Transformer-Recurrent-U Network for Multi-channel Reverberant Sound Source Separation

In recent years, many deep learning techniques for single-channel sound ...
research
05/19/2023

Direction Specific Ambisonics Source Separation with End-To-End Deep Learning

Ambisonics is a scene-based spatial audio format that has several useful...
research
12/10/2022

GPU-accelerated Guided Source Separation for Meeting Transcription

Guided source separation (GSS) is a type of target-speaker extraction me...
research
11/18/2019

Signal Clustering with Class-independent Segmentation

Radar signals have been dramatically increasing in complexity, limiting ...
research
10/13/2021

Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals

Neurophysiological time series, such as electromyographic signal and int...
research
02/14/2020

Sound Event Localization based on Sound Intensity Vector Refined By DNN-Based Denoising and Source Separation

We propose a direction-of-arrival (DOA) estimation method for Sound Even...
research
03/26/2022

Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation

A new learning algorithm for speech separation networks is designed to e...

Please sign up or login with your details

Forgot password? Click here to reset