1 code implementation • 15 May 2023 • Huajian Fang, Dennis Becker, Stefan Wermter, Timo Gerkmann
In this paper, we study the benefits of modeling uncertainty in clean speech estimation.
no code implementations • 27 Mar 2023 • Huajian Fang, Niklas Wittmer, Johannes Twiefel, Stefan Wermter, Timo Gerkmann
In this paper, we propose a multichannel partially adaptive scheme to jointly model ego-noise and environmental noise utilizing the VAE-NMF framework, where we take advantage of spatially and spectrally structured characteristics of ego-noise by pre-training the ego-noise model, while retaining the ability to adapt to unknown environmental noise.
no code implementations • 9 Dec 2022 • Huajian Fang, Timo Gerkmann
Single-channel deep speech enhancement approaches often estimate a single multiplicative mask to extract clean speech without a measure of its accuracy.
no code implementations • 4 Mar 2022 • Huajian Fang, Tal Peer, Stefan Wermter, Timo Gerkmann
Speech enhancement in the time-frequency domain is often performed by estimating a multiplicative mask to extract clean speech.
no code implementations • 17 Feb 2021 • Huajian Fang, Guillaume Carbajal, Stefan Wermter, Timo Gerkmann
Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics.