Keras implementation of Csapó T.G., ,,Speaker dependent acoustic-to-articulatory inversion using real-time MRI of the vocal tract'', accepted at Interspeech 2020, arXiv:2008.02098
USC-TIMIT database at: https://sail.usc.edu/span/usc-timit/
Pretrained models and generated video samples (Jan 29, 2020) at https://simonyi-my.sharepoint.com/:f:/g/personal/csapszi_sch_bme_hu/Eu25AI1rYftLgeLRwU4Y6WkBppWdHTAejfn-pCqM6ZRngw?e=seqB5p
Requirements
- Python 3.6.9
- keras 2.2.4
- tensorflow-gpu 1.13.1
- ...etc... see requirements.txt