DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement

Schröter H, Rosenkranz T, Escalante-B AN, Maier A (2023)

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Conference Proceedings Title: INTERSPEECH 2023

Event location: Dublin, Ireland

Open Access Link: https://arxiv.org/abs/2305.08227

Abstract

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to take advantage of these correlations. In this work, we present a real-time speech enhancement demo using DeepFilterNet. DeepFilterNet's efficiency is enabled by exploiting domain knowledge of speech production and psychoacoustic perception. Our model is able to match state-of-the-art speech enhancement benchmarks while achieving a real-time-factor of 0.19 on a single threaded notebook CPU. The framework as well as pretrained weights have been published under an open source license.

Authors with CRIS profile

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

Related research project(s)

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

Involved external institutions

WS Audiology DE Germany (DE) WS Audiology DK Denmark (DK)

How to cite

APA:

Schröter, H., Rosenkranz, T., Escalante-B, A.N., & Maier, A. (2023). DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement. In INTERSPEECH 2023. Dublin, Ireland.

MLA:

Schröter, Hendrik, et al. "DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement." Proceedings of the INTERSPEECH, Dublin, Ireland 2023.

BibTeX: Download