Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
This work addresses speaker diarization for multi-talker recordings, presenting an incremental improvement over existing approaches.
The paper tackled speaker diarization by extending attractor-based methods to model detailed speaker attributes and using conformers for local dependencies, resulting in improved performance on the CALLHOME dataset.
In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, Encoder-Decoder Attractors (EDA), has been proposed to handle variable speaker counts as well as better guide the network during training. In this study, we extend the attractor paradigm by moving beyond direct speaker modeling and instead focus on representing more detailed `speaker attributes' through a multi-stage process of intermediate representations. Additionally, we enhance the architecture by replacing transformers with conformers, a convolution-augmented transformer, to model local dependencies. Experiments demonstrate improved diarization performance on the CALLHOME dataset.