pith. sign in

arxiv: 2412.13387 · v1 · pith:3SW6HUVDnew · submitted 2024-12-17 · 📡 eess.AS · cs.SD

Deep Speech Synthesis from Multimodal Articulatory Representations

classification 📡 eess.AS cs.SD
keywords synthesismultimodalspeecharticulatorycompareddatadeepimproves
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.