4 citations · 4 across the 6 of their papers we have counts for
6 papers
Efficient Target Activity Detection based on Recurrent Neural Networks
Daniel Gerber, Stefan Meier, Walter Kellermann
This paper addresses the problem of Target Activity Detection (TAD) for binaural listening devices. TAD denotes the problem of robustly detecting the activity of a target speaker i…
HRTF-based two-dimensional robust least-squares frequency-invariant beamformer design for robot audition
Hendrik Barfuss, Michael Buerger, Jasper Podschus +1
In this work, we propose a two-dimensional Head-Related Transfer Function (HRTF)-based robust beamformer design for robot audition, which allows for explicit control of the beamfor…
An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems
Christian Huemmer, Ramón Fernández Astudillo, Walter Kellermann
In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. This numerical sampling concept av…
HRTF-based Robust Least-Squares Frequency-Invariant Polynomial Beamforming
Hendrik Barfuss, Marcel Mueglich, Walter Kellermann
In this work, we propose a robust Head-Related Transfer Function (HRTF)-based polynomial beamformer design which accounts for the influence of a humanoid robot's head on the sound…
Phase-Optimized K-SVD for Signal Extraction from Underdetermined Multichannel Sparse Mixtures
Antoine Deleforge, Walter Kellermann
We propose a novel sparse representation for heavily underdetermined multichannel sound mixtures, i.e., with much more sources than microphones. The proposed approach operates in t…
Improving Blind Source Separation Performance By Adaptive Array Geometries For Humanoid Robots
Hendrik Barfuss, Walter Kellermann
In this paper, the concept of an adaptation algorithm is proposed, which can be used to blindly adapt the microphone array geometry of a humanoid robot such that the performance of…