no code implementations • 22 Feb 2023 • Philipp Götz, Cagdas Tuna, Andreas Walther, Emanuël A. P. Habets
A study is presented in which a contrastive learning approach is used to extract low-dimensional representations of the acoustic environment from single-channel, reverberant speech signals.
1 code implementation • 5 Aug 2022 • Philipp Götz, Cagdas Tuna, Andreas Walther, Emanuël A. P. Habets
A dataset of anechoic recordings of various sound sources encountered in domestic environments is presented.
no code implementations • 23 Feb 2022 • Philipp Götz, Cagdas Tuna, Andreas Walther, Emanuël A. P. Habets
The estimation of reverberation time from real-world signals plays a central role in a wide range of applications.