Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment
This addresses the challenge of cross-modal generation for applications in multimedia and AI, but it is incremental as it builds on existing audio-visual alignment and generation techniques.
The paper tackles the problem of generating images from audio by aligning audio features to a visual latent space and using a pre-trained generator, achieving substantially better results on VEGAS and VGGSound datasets than prior approaches.
How does audio describe the world around us? In this paper, we propose a method for generating an image of a scene from sound. Our method addresses the challenges of dealing with the large gaps that often exist between sight and sound. We design a model that works by scheduling the learning procedure of each model component to associate audio-visual modalities despite their information gaps. The key idea is to enrich the audio features with visual information by learning to align audio to visual latent space. We translate the input audio to visual features, then use a pre-trained generator to produce an image. To further improve the quality of our generated images, we use sound source localization to select the audio-visual pairs that have strong cross-modal correlations. We obtain substantially better results on the VEGAS and VGGSound datasets than prior approaches. We also show that we can control our model's predictions by applying simple manipulations to the input waveform, or to the latent space.