Vu, M., Dat, P. T., Teh, K. K., Nguyen, V. T., & Dat, T. H. (2025). Utilizing Kolmogorov-Arnold Network in Self-Supervised Learning for Speaker Diarization. In (Editor), 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). https://doi.org/10.1109/asru65441.2025.11434699
Abstract:
Speaker diarization is essential in speech processing but remains difficult due to challenges like background noise, far-field audio, overlapping speech, and unknown numbers of speakers. Self-supervised learning (SSL) has recently shown strong performance in neural speaker segmentation (NSS), typically using pre-trained models with Transformer or Conformer decoders connected via a Multi-Layer Perceptron (MLP) adapter. In this work, we enhance the WavLM-Conformer architecture by replacing the MLP with a Kolmogorov-Arnold Network (KAN), which offers better approximation of multivariate functions. Our KAN-based adapter improves the integration of SSL features into downstream tasks. Experiments show that our model achieves consistent gains over existing approaches, setting new state-of-the-art results on challenging diarization benchmarks such as AMI and AISHELL-4. These results demonstrate the promise of KANs in advancing deep learning architectures for speaker diarization.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Industry funded - EC-2023-105
Grant Reference no. : NA