Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Guochen Yu"'
Publikováno v:
IEEE Access, Vol 8, Pp 183272-183285 (2020)
Generative adversarial networks (GANs) have been increasingly used as feature mapping functions in speech enhancement, in which the noisy speech features are transformed to the clean ones through the generators. This article proposes a novel speech e
Externí odkaz:
https://doaj.org/article/2b49fa006ffa4d1f889e6c677bcd0de2
Publikováno v:
International Journal of Circuits, Systems and Signal Processing. 16:1119-1128
The leakage of water in pipelines severely affects the environment and economy. However, there are limitations in the effectiveness of existing leak detection and localization techniques and methodologies. In this paper, we propose a novel leakage de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::efe3430b06348cb0ec24fe6e8b3c927e
https://doi.org/10.46300/9106.2022.16.135
https://doi.org/10.46300/9106.2022.16.135
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30:2156-2172
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::69f5448831b7b01e4532b3d6f20ad28d
https://doi.org/10.1109/taslp.2022.3184889
https://doi.org/10.1109/taslp.2022.3184889
Publikováno v:
2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::076a54987b13886c2a194212b4c7fdff
https://doi.org/10.1109/iscslp57327.2022.10037937
https://doi.org/10.1109/iscslp57327.2022.10037937
Publikováno v:
Speech Communication. 134:42-54
Cycle-consistent generative adversarial networks (CycleGAN) have shown their promising performance for speech enhancement (SE), while one intractable shortcoming of these CycleGAN-based SE systems is that the noise components propagate throughout the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::120880b38fae68620be59697d8839136
https://doi.org/10.1016/j.specom.2021.09.001
https://doi.org/10.1016/j.specom.2021.09.001
Publikováno v:
2022 IEEE 22nd International Conference on Communication Technology (ICCT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a6bc2ccc953169d7fe9db611dd40540
https://doi.org/10.1109/icct56141.2022.10072759
https://doi.org/10.1109/icct56141.2022.10072759
Publikováno v:
2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e3acf1f1da038f61f8699640296a293
https://doi.org/10.23919/apsipaasc55919.2022.9980012
https://doi.org/10.23919/apsipaasc55919.2022.9980012
Publikováno v:
IEEE Access, Vol 8, Pp 183272-183285 (2020)
Generative adversarial networks (GANs) have been increasingly used as feature mapping functions in speech enhancement, in which the noisy speech features are transformed to the clean ones through the generators. This article proposes a novel speech e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0316d02691fe3d41e7a037925a49d47e
https://ieeexplore.ieee.org/document/9216160/
https://ieeexplore.ieee.org/document/9216160/
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:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f005b80d86d01195d3d48da9724f2466
http://arxiv.org/abs/2202.07931
http://arxiv.org/abs/2202.07931
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 performance. Motivated by that, we propose a dual-branch attention-in-attentio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::28724bf483a76b654aa21b5d2f7fda9c
http://arxiv.org/abs/2110.06467
http://arxiv.org/abs/2110.06467