Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition. (arXiv:2201.05554v1 [cs.SD] CROSS LISTED)

Automatic recognition of disordered speech remains a highly challenging task
to date. Sources of variability commonly found in normal speech including
accent, age or gender, when further compounded with the underlying causes of
speech impairment and varying severity levels, create large diversity among
speakers. To this end, speaker adaptation techniques play a vital role in
current speech recognition systems. Motivated by the spectro-temporal level
differences between disordered and normal speech that systematically manifest
in articulatory imprecision, decreased volume and clarity, …

arxiv speech