A system that uses AV-HuBERT to recognize words from rtMRI vocal tract videos and VITS to speak them in a new voice reaches 15.18% WER on USC-TIMIT.
Development and evaluation of pitch adjustable electrolarynx,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MRI2Speech: Speech Synthesis from Articulatory Movements Recorded by Real-time MRI
A system that uses AV-HuBERT to recognize words from rtMRI vocal tract videos and VITS to speak them in a new voice reaches 15.18% WER on USC-TIMIT.