Pruning-aware Loss Functions for STOI-Optimized Pruned Recurrent Autoencoders for the Compression of the Stimulation Patterns of Cochlear Implants at Zero Delay
This work addresses the need for efficient, low-latency compression in cochlear implants, which is crucial for users with profound hearing loss, but it is incremental as it builds on existing pruning methods.
The paper tackles the problem of reducing model size for deep recurrent autoencoders used in cochlear implant audio compression, while maintaining speech intelligibility, by proposing a pruning-aware loss function that yields substantial gains in objective intelligibility scores, especially at pruning rates above 45%, with little degradation observed up to 55% pruning.
Cochlear implants (CIs) are surgically implanted hearing devices, which allow to restore a sense of hearing in people suffering from profound hearing loss. Wireless streaming of audio from external devices to CI signal processors has become common place. Specialized compression based on the stimulation patterns of a CI by deep recurrent autoencoders can decrease the power consumption in such a wireless streaming application through bit-rate reduction at zero latency. While previous research achieved considerable bit-rate reductions, model sizes were ignored, which can be of crucial importance in hearing-aids due to their limited computational resources. This work investigates maximizing objective speech intelligibility of the coded stimulation patterns of deep recurrent autoencoders while minimizing model size. For this purpose, a pruning-aware loss is proposed, which captures the impact of pruning during training. This training with a pruning-aware loss is compared to conventional magnitude-informed pruning and is found to yield considerable improvements in objective intelligibility, especially at higher pruning rates. After fine-tuning, little to no degradation of objective intelligibility is observed up to a pruning rate of about 55\,\%. The proposed pruning-aware loss yields substantial gains in objective speech intelligibility scores after pruning compared to the magnitude-informed baseline for pruning rates above 45\,\%.