Assessing the Robustness of Spectral Clustering for Deep Speaker Diarization
This work addresses robustness issues in speaker diarization for audio processing applications, but it is incremental as it focuses on analyzing an existing method rather than introducing new techniques.
This study tackled the problem of speaker diarization robustness across different domains by examining spectral clustering, revealing that domain mismatch leads to performance differences due to variations in optimal tuning parameters and speaker count estimation, with experiments on AMI and DIHARD corpora showing these trends.
Clustering speaker embeddings is crucial in speaker diarization but hasn't received as much focus as other components. Moreover, the robustness of speaker diarization across various datasets hasn't been explored when the development and evaluation data are from different domains. To bridge this gap, this study thoroughly examines spectral clustering for both same-domain and cross-domain speaker diarization. Our extensive experiments on two widely used corpora, AMI and DIHARD, reveal the performance trend of speaker diarization in the presence of domain mismatch. We observe that the performance difference between two different domain conditions can be attributed to the role of spectral clustering. In particular, keeping other modules unchanged, we show that differences in optimal tuning parameters as well as speaker count estimation originates due to the mismatch. This study opens several future directions for speaker diarization research.