This work investigates the use of large-scale, English-only pre-trained models (CLIP and HuBERT) for multilingual image-speech retrieval. For non-English image-speech retrieval, we outperform the current state-of-the-art performance by a wide margin both when training separate models for each language, and with a single model which processes speech in all three languages. We identify key differences in model behavior and performance between English and non-English settings, attributable to the English-only pre-training of CLIP and HuBERT, and investigate how fine-tuning the pre-trained models impacts these differences. Finally, we show that our models can be used for mono- and cross-lingual speech-text retrieval and cross-lingual speech-speech retrieval, despite never having seen any parallel speech-text or speech-speech data during training.
@article{arxiv.2211.01180,
title = {M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval},
author = {Layne Berry and Yi-Jen Shih and Hsuan-Fu Wang and Heng-Jui Chang and Hung-yi Lee and David Harwath},
journal= {arXiv preprint arXiv:2211.01180},
year = {2023}
}