Abstract:

Self-supervised models such as WavLM have demonstrated strong performance for neural speaker diarization. However, these models are typically pre-trained on single-channel recordings, limiting their effectiveness in multi-channel scenarios. Existing diarization systems built on these models often rely on DOVER-Lap to combine outputs from individual channels. Although effective, this approach incurs substantial computational overhead and fails to fully exploit spatial information. In this work, building on DiariZen, a pipeline that combines WavLM-based local end- to-end neural diarization with speaker embedding clustering, we introduce a lightweight approach to make pre-trained WavLM spatially aware by inserting channel communication modules into the early layers. Our method is agnostic to both the number of micro- phone channels and array topologies, ensuring broad applicability. We further propose to fuse multi-channel speaker embeddings by leveraging spatial attention weights. Evaluations on five public datasets show consistent improvements over single-channel base- lines and demonstrate superior performance and efficiency com- pared with DOVER-Lap.