Published November 24, 2020
| Version v1
Other
Open
SASEGAN models
Description
These are models of the self-attention adversarial generative network for speech enhancement (SEGAN) that are described in:
H. Phan, H. L. Nguyen, O. Y. Chén, P. Koch, N. Q. K. Duong, I. McLoughlin, and A. Mertins, "Self-Attention Generative Adversarial Network for Speech Enhancement," arXiv preprint arXiv:2010.09132, 2020.
Files
segan_allbiased_preemph_att10.zip
Files
(49.4 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:58232aa7da92912fcd1dfbe9117e3152
|
28.3 kB | Download |
|
md5:2367264bab9f3d801a88dbd68c58e108
|
5.6 GB | Preview Download |
|
md5:23ccbb66fbc865fdf8d2cf68968d0b10
|
5.5 GB | Preview Download |
|
md5:1af3c5c69d8543f852710653a59fe037
|
5.5 GB | Preview Download |
|
md5:76bae5001191f8ea4ab8259a847663f4
|
5.5 GB | Preview Download |
|
md5:9816e2d3c0fd87db5d9d7ae7c2819552
|
5.5 GB | Preview Download |
|
md5:1356e792bca3f80b10c5aba7b7203225
|
5.5 GB | Preview Download |
|
md5:4b8bac9b8504c3d99ccb904c30f568e8
|
5.5 GB | Preview Download |
|
md5:2277f16b7daba00b029035cdf2a3018a
|
5.5 GB | Preview Download |
|
md5:7e4be1ed9573b724cc347c692802e149
|
5.6 GB | Preview Download |