Skip to main content
. Author manuscript; available in PMC: 2019 Jun 20.
Published in final edited form as: IEEE/ACM Trans Audio Speech Lang Process. 2018 May 30;26(10):1702–1726. doi: 10.1109/TASLP.2018.2842159

Fig. 7.

Fig. 7.

DNN architecture for speech enhancement with an autoencoder for unsupervised adaptation (from [98]). The AE stacked on top of a DNN serves as a purity checker for estimated clean speech from the bottom DNN. S(1) denotes the spectrum of a speech signal, S(2) the spectrum of a noise signal, and S(1)˜ an estimate of S(1).