Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios
This work addresses speaker diarization for two-speaker conversations, with incremental improvements in error rates.
The paper tackled the problem of improving speaker discriminative capabilities in end-to-end neural diarization systems for two-speaker scenarios, resulting in a 10.78% relative reduction in diarization error rates on the CallHome dataset.
End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to enhance the speaker discriminative capabilities, while maintaining their overlap handling strengths. To achieve this, we propose several methods for incorporating these embeddings along the acoustic features. Furthermore, we delve into an analysis of the correct handling of silence frames, the window length for extracting speaker embeddings and the transformer encoder size. The effectiveness of our proposed approach is thoroughly evaluated on the CallHome dataset for the two-speaker diarization task, with results that demonstrate a significant reduction in diarization error rates achieving a relative improvement of a 10.78% compared to the baseline end-to-end model.