Lightweight Online Noise Reduction on Embedded Devices using Hierarchical Recurrent Neural Networks

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

Event location: Shanghai CN

URI: https://arxiv.org/abs/2006.13067

DOI: 10.21437/interspeech.2020-1131

Open Access Link: https://arxiv.org/abs/2006.13067

Abstract

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.

Authors with CRIS profile

Hendrik Schröter Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

Additional Organisation(s)

Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) (LME)

Related research project(s)

Deep Learning based Noise Reduction for Hearing Aids Feb. 1, 2019 - Jan. 31, 2023

Involved external institutions

Sivantos GmbH DE Germany (DE)

How to cite

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