Improvement of Noise Suppression Performance of SEGAN by Sparse Latent Vectors

For the purpose of speech enhancement, SEGAN, which is one of deep generative models, has attracted attention due to its high performance. In this paper, we propose a method to sparse latent vectors to further enhance the noise suppression effect of SEGAN.

[1]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Antonio Bonafonte,et al.  SEGAN: Speech Enhancement Generative Adversarial Network , 2017, INTERSPEECH.

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  David Malah,et al.  Speech enhancement using a minimum mean-square error log-spectral amplitude estimator , 1984, IEEE Trans. Acoust. Speech Signal Process..

[5]  Akihiko Sugiyama,et al.  Noise Suppression with High Speech Quality Based on Weighted Noise Estimation and MMSE STSA , 2002, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..