Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Yu, Guochen"'
Autor:
Yu, Guochen, Han, Runqiang, Xu, Chenglin, Zhao, Haoran, Li, Nan, Zhang, Chen, Zheng, Xiguang, Zhou, Chao, Huang, Qi, Yu, Bing
This paper presents the speech restoration and enhancement system created by the 1024K team for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. Our system consists of a generative adversarial network (GAN) in complex-domain for speech rest
Externí odkaz:
http://arxiv.org/abs/2402.01808
Autor:
Yu, Guochen, Zheng, Xiguang, Li, Nan, Han, Runqiang, Zheng, Chengshi, Zhang, Chen, Zhou, Chao, Huang, Qi, Yu, Bing
Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact that the
Externí odkaz:
http://arxiv.org/abs/2312.13722
While deep neural networks have facilitated significant advancements in the field of speech enhancement, most existing methods are developed following either empirical or relatively blind criteria, lacking adequate guidelines in pipeline design. Insp
Externí odkaz:
http://arxiv.org/abs/2211.16764
Despite the promising performance of existing frame-wise all-neural beamformers in the speech enhancement field, it remains unclear what the underlying mechanism exists. In this paper, we revisit the beamforming behavior from the beam-space dictionar
Externí odkaz:
http://arxiv.org/abs/2211.12024
Real-time communications in packet-switched networks have become widely used in daily communication, while they inevitably suffer from network delays and data losses in constrained real-time conditions. To solve these problems, audio packet loss conc
Externí odkaz:
http://arxiv.org/abs/2207.01255
While the deep learning techniques promote the rapid development of the speech enhancement (SE) community, most schemes only pursue the performance in a black-box manner and lack adequate model interpretability. Inspired by Taylor's approximation the
Externí odkaz:
http://arxiv.org/abs/2205.00206
Due to the high computational complexity to model more frequency bands, it is still intractable to conduct real-time full-band speech enhancement based on deep neural networks. Recent studies typically utilize the compressed perceptually motivated fe
Externí odkaz:
http://arxiv.org/abs/2203.16033
While existing end-to-end beamformers achieve impressive performance in various front-end speech processing tasks, they usually encapsulate the whole process into a black box and thus lack adequate interpretability. As an attempt to fill the blank, w
Externí odkaz:
http://arxiv.org/abs/2203.07195
For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in Bark and E
Externí odkaz:
http://arxiv.org/abs/2203.00472
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 i.e., magnitude-only recovery and the residual complex spectrum estimation)}, r
Externí odkaz:
http://arxiv.org/abs/2202.07931