A study of the robustness of raw waveform based speaker embeddings under mismatched conditions
This work addresses robustness issues in speaker verification for cross-dataset scenarios, but it is incremental as it builds on existing raw waveform methods.
The study tackled the problem of raw waveform-based speaker embeddings performing poorly under mismatched conditions, finding significant performance degradation compared to spectral systems, and proposed two strategies to improve cross-dataset robustness.
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.