# Semi-supervised multi-channel speaker diarization with cross-channel attention

arXiv: https://arxiv.org/abs/2307.08688 · HTML: https://mlsanity.com/paper/2307.08688/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2023.

## Built on by (most cited first, 3 of 3)

- [EmoDiarize: Speaker Diarization and Emotion Identification from Speech Signals using Convolutional Neural Networks](https://mlsanity.com/paper/2310.12851/) (2023)
- [From Modular to End-to-End Speaker Diarization](https://mlsanity.com/paper/2407.08752/) (2024)
- [Exploring Speaker Diarization with Mixture of Experts](https://mlsanity.com/paper/2506.14750/) (2025)

## Abstract (arXiv)

Most neural speaker diarization systems rely on sufficient manual training data labels, which are hard to collect under real-world scenarios. This paper proposes a semi-supervised speaker diarization system to utilize large-scale multi-channel training data by generating pseudo-labels for unlabeled data. Furthermore, we introduce cross-channel attention into the Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding (NSD-MA-MSE) to learn channel contextual information of speaker embeddings better. Experimental results on the CHiME-7 Mixer6 dataset which only contains partial speakers' labels of the training set, show that our system achieved 57.01% relative DER reduction compared to the clustering-based model on the development set. We further conducted experiments on the CHiME-6 dataset to simulate the scenario of missing partial training set labels. When using 80% and 50% labeled training data, our system performs comparably to the results obtained using 100% labeled data for training.