Optimal hearing aid design through restoration of the neural code
Drakopoulos, F.; Pellatt, L.; Sabesan, S.; Xia, Y.; Fragner, A.; Lesica, N. A.
Show abstract
Hearing loss introduces complex distortions in the neural coding of sound that current hearing aids fail to address. Here, we leverage tools for neural control via deep learning to identify novel sound processing strategies to correct these distortions. We use large-scale intracranial recordings from the gerbil inferior colliculus to train deep neural network models of neural coding (ICNets) to serve as in silico surrogates for brains with normal and impaired hearing. We then use the ICNets to train another network (AidNet) to act as an optimal hearing aid, providing the individualized sound processing required to elicit normal neural activity in impaired brains. We find that AidNet outperforms state-of-the-art hearing aid processing by a wide margin in correcting both distortions in neural coding and deficits in simulated phoneme recognition. This successful demonstration of neural restoration via closed-loop optimization opens up new possibilities for improving not only hearing aids, but also other sensory devices and neurotechnologies.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Modeling neural coding in the auditory midbrain with high resolution and accuracy 98%
- A Neural Speech Decoding Framework Leveraging Deep Learning and Speech Synthesis 96%
- Parallel hierarchical encoding of linguistic representations in the human auditory cortex and recurrent automatic speech recognition systems 94%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Deep neural network models reveal interplay of peripheral coding and stimulus statistics in pitch perception 95%
- The impact of musical expertise on disentangled and contextual neural encoding of music revealed by generative music models 93%
- Convergent neural signatures of speech prediction error are a biological marker for spoken word recognition 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.