WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words
This work addresses the problem of enhancing language models with multimodal inputs for researchers, but it is incremental as it builds on existing text-image approaches.
The paper tackled whether multimodal text-audio training improves language model quality and efficiency, finding that WhisBERT performed well on multimodal tasks and surpassed baselines but struggled to outperform its text-only version.
Training on multiple modalities of input can augment the capabilities of a language model. Here, we ask whether such a training regime can improve the quality and efficiency of these systems as well. We focus on text--audio and introduce Whisbert, which is inspired by the text--image approach of FLAVA (Singh et al., 2022). In accordance with Babylm guidelines (Warstadt et al., 2023), we pretrain Whisbert on a dataset comprising only 100 million words plus their corresponding speech from the word-aligned version of the People's Speech dataset (Galvez et al., 2021). To assess the impact of multimodality, we compare versions of the model that are trained on text only and on both audio and text simultaneously. We find that while Whisbert is able to perform well on multimodal masked modeling and surpasses the Babylm baselines in most benchmark tasks, it struggles to optimize its complex objective and outperform its text-only Whisbert baseline.