1 code implementation • 9 Aug 2022 • Axel Berg, Mark O'Connor, Kalle Åström, Magnus Oskarsson
Speaker localization using microphone arrays depends on accurate time delay estimation techniques.
1 code implementation • 8 Apr 2022 • Axel Berg, Magnus Oskarsson, Mark O'Connor
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial.
Ranked #6 on Point Cloud Registration on 3DMatch Benchmark
9 code implementations • 1 Apr 2021 • Axel Berg, Mark O'Connor, Miguel Tairum Cruz
The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition.
Ranked #5 on Keyword Spotting on Google Speech Commands (using extra training data)
1 code implementation • 29 Jun 2020 • Axel Berg, Magnus Oskarsson, Mark O'Connor
By discretizing the target into a set of non-overlapping classes, it has been shown that training a classifier can improve neural network accuracy compared to using a standard regression approach.
Ranked #2 on Head Pose Estimation on BIWI (MAE (trained with BIWI data) metric)