all AI news
Investigation of Data Augmentation Techniques for Disordered Speech Recognition. (arXiv:2201.05562v1 [cs.SD] CROSS LISTED)
cs.LG updates on arXiv.org arxiv.org
Disordered speech recognition is a highly challenging task. The underlying
neuro-motor conditions of people with speech disorders, often compounded with
co-occurring physical disabilities, lead to the difficulty in collecting large
quantities of speech required for system development. This paper investigates a
set of data augmentation techniques for disordered speech recognition,
including vocal tract length perturbation (VTLP), tempo perturbation and speed
perturbation. Both normal and disordered speech were exploited in the
augmentation process. Variability among impaired speakers in both the original …
arxiv augmentation data investigation speech speech recognition