Skip to main content
. Author manuscript; available in PMC: 2019 Apr 2.
Published in final edited form as: IEEE/ACM Trans Audio Speech Lang Process. 2017 Feb 13;25(5):952–964. doi: 10.1109/TASLP.2017.2667879

Fig. 7.

Fig. 7.

Neural network architecture setting. There are five inputs, one output and three hidden layers. The first layer has 10 linear units. The second and third layer have 6 and 5 sigmoid units respectively.