ABC0408 / WaveImage

vocoder

in the wave-image.ipynb file, It provides a way to build a bridge between pictures and voice.

Plan

After convert audio to wave-image, now my task also change to image to image translation.

• Part1： read some papers about image-to-image translation
• Part2： thinking about the difference between wave-image and others real world image

Part 1:

Papers

1. • Pix2Pix Image-to-Image Translation with Conditional Adversarial Networks [paper] [code] [notes]
2. • Pix2PixHD High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs [paper] [code] [notes]
3. • CycleGAN Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [paper] [code] [notes]
4. • BicycleGAN Toward Multimodal Image-to-Image Translation [paper] [code] [notes]

Part 2:

1. the object in the image has their own shape, color ,,,. In the wave-image, it consists of different words. Each word has their own shape, color.