Schröter H, Rosenkranz T, Escalante Banuelos A, Zobel P, Maier A (2020)
Publication Type: Conference contribution, Original article
Publication year: 2020
Conference Proceedings Title: INTERSPEECH 2020
URI: https://arxiv.org/abs/2006.13067
DOI: 10.21437/interspeech.2020-1131
Open Access Link: https://arxiv.org/abs/2006.13067
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.
APA:
Schröter, H., Rosenkranz, T., Escalante Banuelos, A., Zobel, P., & Maier, A. (2020). Lightweight Online Noise Reduction on Embedded Devices using Hierarchical Recurrent Neural Networks. In INTERSPEECH 2020. Shanghai, CN.
MLA:
Schröter, Hendrik, et al. "Lightweight Online Noise Reduction on Embedded Devices using Hierarchical Recurrent Neural Networks." Proceedings of the INTERSPEECH 2020, Shanghai 2020.
BibTeX: Download