Skip to main content
Fig. 3 | EURASIP Journal on Wireless Communications and Networking

Fig. 3

From: Improved Wasserstein conditional generative adversarial network speech enhancement

Fig. 3

The structure of speech enhancement WCGAN. The resulting dimensions per layer is 16,384 × 1, 8192 × 16, 4096 × 32, 2048 × 32, 1024 × 64, 512 × 64, 256 × 128, 128 × 128, 64 × 256, 32 × 256, 16 × 512, and 8 × 1024. The decoder stage of G is a mirroring of the encoder with the same filter widths and the same amount of filters per layer. The residual network makes training stable and noisy speech vector makes the number of feature maps in every layer to be doubled

Back to article page