LSTM Based Similarity Measurement with Spectral Clustering for Speaker Diarization

Qingjian Lin, Ruiqing Yin, Ming Li, Hervé Bredin, Claude Barras


More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction. Still, in the clustering stage, traditional algorithms like probabilistic linear discriminant analysis (PLDA) are widely used for scoring the similarity between two speech segments. In this paper, we propose a supervised method to measure the similarity matrix between all segments of an audio recording with sequential bidirectional long short-term memory networks (Bi-LSTM). Spectral clustering is applied on top of the similarity matrix to further improve the performance. Experimental results show that our system significantly outperforms the state-of-the-art methods and achieves a diarization error rate of 6.63% on the NIST SRE 2000 CALLHOME database.


 DOI: 10.21437/Interspeech.2019-1388

Cite as: Lin, Q., Yin, R., Li, M., Bredin, H., Barras, C. (2019) LSTM Based Similarity Measurement with Spectral Clustering for Speaker Diarization. Proc. Interspeech 2019, 366-370, DOI: 10.21437/Interspeech.2019-1388.


@inproceedings{Lin2019,
  author={Qingjian Lin and Ruiqing Yin and Ming Li and Hervé Bredin and Claude Barras},
  title={{LSTM Based Similarity Measurement with Spectral Clustering for Speaker Diarization}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={366--370},
  doi={10.21437/Interspeech.2019-1388},
  url={http://dx.doi.org/10.21437/Interspeech.2019-1388}
}