Zobrazeno 1 - 10
of 169
pro vyhledávání: '"Li, Andong"'
The proliferation of deep neural networks has spawned the rapid development of acoustic echo cancellation and noise suppression, and plenty of prior arts have been proposed, which yield promising performance. Nevertheless, they rarely consider the de
Externí odkaz:
http://arxiv.org/abs/2406.11175
Autor:
Liu, Wenzhe, Shi, Yupeng, Chen, Jun, Rao, Wei, He, Shulin, Li, Andong, Wang, Yannan, Wu, Zhiyong
This paper describes a real-time General Speech Reconstruction (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This novel proposed system is a two-stage architecture, in which the speech restoration is performe
Externí odkaz:
http://arxiv.org/abs/2306.08454
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
While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural networks but
Externí odkaz:
http://arxiv.org/abs/2203.07179
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