no code implementations • 8 Dec 2023 • Nils L. Westhausen, Bernd T. Meyer
In this paper, we introduce a causal low-latency low-complexity approach for binaural multichannel blind speaker separation in noisy reverberant conditions.
no code implementations • 17 Jul 2023 • Nils L. Westhausen, Bernd T. Meyer
The performance of an oracle binaural LCMV beamformer in non-low-latency configuration can be matched even by a unilateral configuration of the GCFSnet in terms of objective metrics.
1 code implementation • 4 Apr 2022 • Nils L. Westhausen, Bernd T. Meyer
The model with the lowest complexity described in this paper reaches a robust PLC performance and consistent improvements over the zero-filling baseline for all metrics.
no code implementations • 3 Nov 2021 • Marko Stamenovic, Nils L. Westhausen, Li-Chia Yang, Carl Jensen, Alex Pawlicki
Using weight pruning, we show that we are able to compress an already compact model's memory footprint by a factor of 42x from 3. 7MB to 87kB while only losing 0. 1 dB SDR in performance.
no code implementations • 2 Nov 2021 • Nils L. Westhausen, Rainer Huber, Hannah Baumgartner, Ragini Sinha, Jan Rennies, Bernd T. Meyer
Listening to the audio of TV broadcast signals can be challenging for hearing-impaired as well as normal-hearing listeners, especially when background sounds are prominent or too loud compared to the speech signal.
1 code implementation • 27 Oct 2020 • Nils L. Westhausen, Bernd T. Meyer
This paper applies the dual-signal transformation LSTM network (DTLN) to the task of real-time acoustic echo cancellation (AEC).
2 code implementations • Interspeech 2020 • Nils L. Westhausen, Bernd T. Meyer
This paper introduces a dual-signal transformation LSTM network (DTLN) for real-time speech enhancement as part of the Deep Noise Suppression Challenge (DNS-Challenge).
Ranked #2 on Speech Enhancement on WHAMR!
Speech Enhancement Audio and Speech Processing Sound