Skip to main content
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:12:57
11 May 2022

In this paper, we conduct a cross-dataset study on parametric and non-parametric raw-waveform based speaker embeddings through speaker verification experiments. In general, we observe a more significant performance degradation of these raw-waveform systems compared to spectral based systems. We then propose two strategies to improve the performance of raw-waveform based systems on cross-dataset tests. The first strategy is to change the real-valued filters into analytic filters to ensure shift-invariance. The second strategy is to apply variational dropout to non-parametric filters to prevent them from overfitting irrelevant nuance features. By combining these strategies, we achieve results comparable to spectral based systems on both the VoxCeleb and VOiCEs datasets. Futhermore, we demonstrate that the learned filters carry little noise compared to existing non-parametric learnable front-ends.

More Like This

  • CIS
    Members: Free
    IEEE Members: Free
    Non-members: Free
  • CIS
    Members: Free
    IEEE Members: Free
    Non-members: Free
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00