Translating speech with just images
Abstract
Visually grounded speech models link speech to images. We extend this connection by linking images to text via an existing image captioning system, and as a result gain the ability to map speech audio directly to text. This approach can be used for speech translation with just images by having the audio in a different language from the generated captions. We investigate such a system on a real low-resource language, Yor\`ub\'a, and propose a Yor\`ub\'a-to-English speech translation model that leverages pretrained components in order to be able to learn in the low-resource regime. To limit overfitting, we find that it is essential to use a decoding scheme that produces diverse image captions for training. Results show that the predicted translations capture the main semantics of the spoken audio, albeit in a simpler and shorter form.
Keywords
Cite
@article{arxiv.2406.07133,
title = {Translating speech with just images},
author = {Dan Oneata and Herman Kamper},
journal= {arXiv preprint arXiv:2406.07133},
year = {2024}
}
Comments
Accepted at Interspeech 2024