Deep recurrent autoencoders convert images to shortened audio signals that incorporate hearing models, enabling above-chance hand posture discrimination and object reaching after a few hours of training instead of months.
Audio–Vision Substitution for Blind Individu- als: Addressing Human Information Processing Capacity Limitations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.NC 1years
2019 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Autoencoding sensory substitution
Deep recurrent autoencoders convert images to shortened audio signals that incorporate hearing models, enabling above-chance hand posture discrimination and object reaching after a few hours of training instead of months.