The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a multimodal pre-training framework. On single-speaker speech synthesis tasks from real-time magnetic resonance imaging and surface electromyography inputs, the intelligibility of synthesized outputs improves noticeably. For example, compared to prior work, utilizing our proposed transfer learning methods improves the MRI-to-speech performance by 36% word error rate. In addition to these intelligibility results, our multimodal pre-trained models consistently outperform unimodal baselines on three objective and subjective synthesis quality metrics.
@article{arxiv.2412.13387,
title = {Deep Speech Synthesis from Multimodal Articulatory Representations},
author = {Peter Wu and Bohan Yu and Kevin Scheck and Alan W Black and Aditi S. Krishnapriyan and Irene Y. Chen and Tanja Schultz and Shinji Watanabe and Gopala K. Anumanchipalli},
journal= {arXiv preprint arXiv:2412.13387},
year = {2024}
}