/mri2speech

Articulatory-to-acoustic mapping using real-time MRI

Primary LanguagePythonOtherNOASSERTION

mri2speech

Keras implementation of Csapó T.G., ,,Speaker dependent articulatory-to-acoustic mapping using real-time MRI of the vocal tract'', accepted at Interspeech 2020, arXiv:2008.00889

USC-TIMIT database at: https://sail.usc.edu/span/usc-timit/

Pretrained models and synthesized samples (Jan 16, 2020) at https://simonyi-my.sharepoint.com/:f:/g/personal/csapszi_sch_bme_hu/EqPHlfuXpulEip9xVu42q7kBqaVmhrcaN6W3PnU-qEtPhA?e=EKPe9l

Requirements

  • Python 3.6.9
  • keras 2.2.4
  • tensorflow-gpu 1.13.1
  • ...etc... see requirements.txt