K Li, G Chen - arXiv preprint arXiv:2404.02063, 2024 - arxiv.org
In speech separation, both CNN-and Transformer-based models have demonstrated robust separation capabilities, garnering significant attention within the research community …
K Tesch, T Gerkmann - IEEE/ACM Transactions on Audio …, 2023 - ieeexplore.ieee.org
In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the …
S Nie, H Zhang, XL Zhang… - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
In many present speech separation approaches, the separation task is formulated as a binary classification problem. Several classification-based approaches have been proposed …
C Fan, J Tao, B Liu, J Yi, Z Wen, X Liu - arXiv preprint arXiv:2003.07544, 2020 - arxiv.org
In this paper, we propose an end-to-end post-filter method with deep attention fusion features for monaural speaker-independent speech separation. At first, a time-frequency …
Z Mu, X Yang, W Zhu - ICASSP 2023-2023 IEEE International …, 2023 - ieeexplore.ieee.org
Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information …
This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to …
K Li, R Yang, X Hu - arXiv preprint arXiv:2209.15200, 2022 - arxiv.org
Deep neural networks have shown excellent prospects in speech separation tasks. However, obtaining good results while keeping a low model complexity remains challenging …
Z Zhang, B He, Z Zhang - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
Speech separation is an important problem in speech processing, which targets to separate and generate clean speech from a mixed audio containing speech from different speakers …
J Luo, J Wang, N Cheng, E Xiao, X Zhang… - arXiv preprint arXiv …, 2022 - arxiv.org
Time-domain Transformer neural networks have proven their superiority in speech separation tasks. However, these models usually have a large number of network …