1 code implementation • 21 Feb 2024 • Nik Vaessen, David A. van Leeuwen
We then show that the quality of the pre-trained model depends mainly on the amount of speech data seen during training, i. e., on the product of batch size and number of iterations.
1 code implementation • 30 Jun 2023 • Loes Van Bemmel, Zhuoran Liu, Nik Vaessen, Martha Larson
Currently, the common practice for developing and testing gender protection algorithms is "neural-on-neural", i. e., perturbations are generated and tested with a neural network.
no code implementations • 18 Feb 2023 • Tijn Berns, Nik Vaessen, David A. van Leeuwen
We investigate recent transformer networks pre-trained for automatic speech recognition for their ability to detect speaker and language changes in speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 28 Mar 2022 • Nik Vaessen, David A. van Leeuwen
These subsets are restricted to 50\, k audio files (versus over 1\, M files available), and vary on the axis of number of speakers and session variability.
1 code implementation • 30 Sep 2021 • Nik Vaessen, David A. van Leeuwen
This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition.
Ranked #2 on Speaker Recognition on VoxCeleb1