DBNET: DOA-driven beamforming network for end-to-end farfield sound source separation
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A consolidated view of loss functions for supervised deep learning-based speech enhancement2021
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source SeparationIEEE Journal of Selected Topics in Signal Processing, 2019
- Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained With Noise SignalsIEEE Journal of Selected Topics in Signal Processing, 2019
- Phase-Sensitive Joint Learning Algorithms for Deep Learning-Based Speech EnhancementIEEE Signal Processing Letters, 2018
- Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Beamforming: a versatile approach to spatial filteringIEEE ASSP Magazine, 1988
- Image method for efficiently simulating small-room acousticsThe Journal of the Acoustical Society of America, 1979