Multi-scale speech enhancement
The speech stored in this git is enhanced by our MSNet. We evaluate the performance on two datasets.
(1) An open-source dataset [1].
(2) A large-scale dataset (Designed and generated by ourselves).
In this Git, enhanced speech and models are uploaded.
In the folder appendix, more explanations about model structure and hyper-parameters will be added.
If you have questions please contact: Email: lichenxing2015@ia.ac.cn
References: [1] Cassia Valentini-Botinhao, Xin Wang, Shinji Takaki, and Junichi Yamagishi, “Investigating rnn-based speech enhancement methods for noise-robust text-to-speech,” in 9th ISCA Speech Synthesis Workshop, pp. 146–152.