The learnt models in the latter domain can then be used for a diverse set of tasks in a zero-shot way, similar to "Contrastive Language-Image

In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST.

We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models and optimized data-efficiently for spoken language tasks.

Recent accelerations in multi-modal applications have been made possible with the plethora of image and text data available online.