Lightweight Online Noise Reduction on Embedded Devices using Hierarchical Recurrent Neural Networks
This work addresses the challenge of deploying noise reduction algorithms on resource-constrained embedded devices, which is an incremental improvement over existing methods.
The paper tackled the problem of enabling deep-learning-based noise reduction on embedded devices like hearing aids by proposing a hierarchical recurrent neural network approach that drastically reduces parameters and computational requirements while maintaining noise reduction quality, achieving a model with only 5k parameters.
Deep-learning based noise reduction algorithms have proven their success especially for non-stationary noises, which makes it desirable to also use them for embedded devices like hearing aids (HAs). This, however, is currently not possible with state-of-the-art methods. They either require a lot of parameters and computational power and thus are only feasible using modern CPUs. Or they are not suitable for online processing, which requires constraints like low-latency by the filter bank and the algorithm itself. In this work, we propose a mask-based noise reduction approach. Using hierarchical recurrent neural networks, we are able to drastically reduce the number of neurons per layer while including temporal context via hierarchical connections. This allows us to optimize our model towards a minimum number of parameters and floating-point operations (FLOPs), while preserving noise reduction quality compared to previous work. Our smallest network contains only 5k parameters, which makes this algorithm applicable on embedded devices. We evaluate our model on a mixture of EUROM and a real-world noise database and report objective metrics on unseen noise.