100 citations · 127 across the 7 of their papers we have counts for
4 papers · 1 filter
The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning
Nik Vaessen, David A. van Leeuwen
Foundation models in speech are often trained using many GPUs, which implicitly leads to large effective batch sizes. In this paper we study the effect of batch size on pre-trainin…
Towards multi-task learning of speech and speaker recognition
Nik Vaessen, David A. van Leeuwen
We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads.…
Training speaker recognition systems with limited data
Nik Vaessen, David A. van Leeuwen
This work considers training neural networks for speaker recognition with a much smaller dataset size compared to contemporary work. We artificially restrict the amount of data by…
Fine-tuning wav2vec2 for speaker recognition
Nik Vaessen, David A. van Leeuwen
This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recog…