Two heads are better than one: A two-stage complex spectral map** approach for monaural speech enhancement

A Li, W Liu, C Zheng, C Fan, X Li - IEEE/ACM Transactions on …, 2021‏ - ieeexplore.ieee.org
For challenging acoustic scenarios as low signal-to-noise ratios, current speech
enhancement systems usually suffer from performance bottleneck in extracting the target …

ADL-MVDR: All deep learning MVDR beamformer for target speech separation

Z Zhang, Y Xu, M Yu, SX Zhang… - ICASSP 2021-2021 …, 2021‏ - ieeexplore.ieee.org
Speech separation algorithms are often used to separate the target speech from other
interfering sources. However, purely neural network based speech separation systems often …

Dual-branch attention-in-attention transformer for single-channel speech enhancement

G Yu, A Li, C Zheng, Y Guo, Y Wang… - ICASSP 2022-2022 …, 2022‏ - ieeexplore.ieee.org
Curriculum learning begins to thrive in the speech enhancement area, which decouples the
original spectrum estimation task into multiple easier sub-tasks to achieve better …

Revisiting denoising diffusion probabilistic models for speech enhancement: Condition collapse, efficiency and refinement

W Tai, F Zhou, G Trajcevski, T Zhong - Proceedings of the AAAI …, 2023‏ - ojs.aaai.org
Recent literature has shown that denoising diffusion probabilistic models (DDPMs) can be
used to synthesize high-fidelity samples with a competitive (or sometimes better) quality than …

DBT-Net: Dual-branch federative magnitude and phase estimation with attention-in-attention transformer for monaural speech enhancement

G Yu, A Li, H Wang, Y Wang, Y Ke… - IEEE/ACM Transactions …, 2022‏ - ieeexplore.ieee.org
The decoupling-style concept begins to ignite in the speech enhancement area, which
decouples the original complex spectrum estimation task into multiple easier sub-tasks (ie …

Deepresgru: residual gated recurrent neural network-augmented kalman filtering for speech enhancement and recognition

N Saleem, J Gao, MI Khattak, HT Rauf, S Kadry… - Knowledge-Based …, 2022‏ - Elsevier
With the recent research developments, deep learning models are powerful alternatives for
speech enhancement and recognition in many real-world applications. Although state-of-the …

Multi-channel multi-frame ADL-MVDR for target speech separation

Z Zhang, Y Xu, M Yu, SX Zhang, L Chen… - … on Audio, Speech …, 2021‏ - ieeexplore.ieee.org
Many purely neural network based speech separation approaches have been proposed to
improve objective assessment scores, but they often introduce nonlinear distortions that are …

Self-attention generative adversarial network for speech enhancement

H Phan, H Le Nguyen, OY Chén, P Koch… - ICASSP 2021-2021 …, 2021‏ - ieeexplore.ieee.org
Existing generative adversarial networks (GANs) for speech enhancement solely rely on the
convolution operation, which may obscure temporal dependencies across the sequence …

A General Unfolding Speech Enhancement Method Motivated by Taylor's Theorem

A Li, G Yu, C Zheng, W Liu, X Li - IEEE/ACM Transactions on …, 2023‏ - ieeexplore.ieee.org
While deep neural networks have facilitated significant advancements in the field of speech
enhancement, most existing methods are developed following either empirical or relatively …

Exploring self-attention mechanisms for speech separation

C Subakan, M Ravanelli, S Cornell… - … on Audio, Speech …, 2023‏ - ieeexplore.ieee.org
Transformers have enabled impressive improvements in deep learning. They often
outperform recurrent and convolutional models in many tasks while taking advantage of …