ADL-MVDR: All Deep Learning MVDR Beamformer For Target Speech Separation
2020 · Zhuohuang Zhang, Yong Xu, Meng Yu, et al.
Abstract
Speech separation algorithms are often used to separate the target speech from other interfering sources. However, purely neural network based speech separation systems often cause nonlinear distortion that is harmful for automatic speech recognition (ASR) systems. The conventional mask-based minimum variance distortionless response (MVDR) beamformer can be used to minimize the distortion, but comes with high level of residual noise. Furthermore, the matrix operations (e.g., matrix inversion) involved in the conventional MVDR solution are sometimes numerically unstable when jointly trained with neural networks. In this paper, we propose a novel all deep learning MVDR framework, where the matrix inversion and eigenvalue decomposition are replaced by two recurrent neural networks (RNNs), to resolve both issues at the same time. The proposed method can greatly reduce the residual noise while keeping the target speech undistorted by leveraging on the RNN-predicted frame-wise beamforming we
Authors
(none)
Tags
Stats
Related papers
- Multi-channel Multi-frame ADL-MVDR For Target Speech Separation (2020)0.00
- Unsupervised Speech Enhancement Based On Multichannel Nmf-informed Beamforming For Noise-robust Automatic Speech Recognition (2019)13.23
- Dnn-free Low-latency Adaptive Speech Enhancement Based On Frame-online Beamforming Powered By Block-online Fastmnmf (2022)0.00
- Multichannel Loss Function For Supervised Speech Source Separation By Mask-based Beamforming (2019)7.50
- Sequential Multi-frame Neural Beamforming For Speech Separation And Enhancement (2019)0.00
- Dual-path Transformer Based Neural Beamformer For Target Speech Extraction (2023)0.00
- Locate And Beamform: Two-dimensional Locating All-neural Beamformer For Multi-channel Speech Separation (2023)3.58
- Deep Ad-hoc Beamforming Based On Speaker Extraction For Target-dependent Speech Separation (2020)7.50