Automatic Restoration of Diacritics for Speech Data Sets.

Sara Abedalmonem Mohammad Shatnawi Sawsan Alqahtani Hanan Aldarmaki

Published in: NAACL-HLT (2024)

Keyphrases

data sets
speech recognition
fully automatic
image restoration
speech music discrimination
automatic speech recognition
semi automatic
synthetic data
super resolution
input data
user interface
benchmark data sets
image processing
real world data sets
speech synthesis
recognition engine
neural network