We propose IM2WAV, an image guided open-domain audio generation system. Given an input image or a sequence of images, IM2WAV generates a semantically relevant sound. IM2WAV is based on two Transformer language models, that operate over a hierarchical discrete audio representation obtained from a VQ-VAE based model. We first produce a low-level audio representation using a language model. Then, we upsample the audio tokens using an additional language model to generate a high-fidelity audio sample. We use the rich semantics of a pre-trained CLIP (Contrastive Language-Image Pre-training)  model embedding as a visual representation to condition the language model. In addition, to steer the generation process towards the conditioning image, we apply the classifier-free guidance method. Results suggest that IM2WAV significantly outperforms the evaluated baselines in both fidelity and relevance evaluation metrics. Additionally, we provide an ablation study to better assess the impact of each of the method components on overall performance. Lastly, to better evaluate image-to-audio models, we propose an out-of-domain image dataset, denoted as IM-AGEHEAR. IMAGEHEAR can be used as a benchmark for evaluating future image-to-audio models. Samples and code can be found under the following link.
|Title of host publication
|ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - 2023
|48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: 4 Jun 2023 → 10 Jun 2023
|ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
|48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
|4/06/23 → 10/06/23
Bibliographical notePublisher Copyright:
© 2023 IEEE.