arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.03089cs.SDeess.AS
收藏

我听到你的真实色彩:图像引导音频生成

I Hear Your True Colors: Image Guided Audio Generation

The Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Roy Sheffer, Yossi Adi

摘要:

我们提出了Im 2 Wav,一个图像引导的开放域音频生成系统。给定输入图像或图像序列,Im 2 Wav生成语义相关的声音。Im 2 Wav基于两个Transformer语言模型,其在从基于VQ-VAE的模型获得的分层离散音频表示上操作。我们首先使用语言模型产生低级音频表示。然后,我们使用附加的语言模型对音频令牌进行上采样以生成高保真音频样本。我们使用预训练的CLIP(对比图像预训练)嵌入的丰富语义作为视觉表示来调节语言模型。此外,为了将生成过程转向调节图像,我们应用了无分类器引导方法。结果表明,Im 2 Wav在保真度和相关性评估指标方面均显着优于评估基线。此外,我们提供了消融研究,以更好地评估每个方法组件对整体性能的影响。最后,为了更好地评估图像到音频模型,我们提出了一个域外图像数据集,表示为ImageHear。ImageHear可以用作评估未来图像到音频模型的基准。样本和代码可以在手稿中找到。

英文摘要:

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) 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 ImageHear. ImageHear can be used as a benchmark for evaluating future image-to-audio models. Samples and code can be found inside the manuscript.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑